phenotypic.enhance.FocusEdgeColorPhase#

class phenotypic.enhance.FocusEdgeColorPhase(*, color_space: Literal['lab', 'hsv'] = 'lab', fusion: Literal['joint', 'coherent', 'l2'] = 'joint', chroma_weight_1: Annotated[float, Ge(ge=0.0), TuneSpec(low=0.0, high=8.0, step=None, log=False, categories=None, tunable=True)] = 1.0, chroma_weight_2: Annotated[float, Ge(ge=0.0), TuneSpec(low=0.0, high=8.0, step=None, log=False, categories=None, tunable=True)] = 1.0, lift: Literal['monogenic', 'conformal'] = 'monogenic', n_scale: Annotated[int, Ge(ge=2), TuneSpec(low=3, high=6, step=None, log=False, categories=None, tunable=True)] = 4, min_wavelength: Annotated[float, Ge(ge=2.0), TuneSpec(low=2.0, high=10.0, step=None, log=False, categories=None, tunable=True)] = 3.0, mult: Annotated[float, Gt(gt=1.0), TuneSpec(low=1.5, high=3.0, step=None, log=False, categories=None, tunable=True)] = 2.1, sigma_onf: Annotated[float, Ge(ge=0.1), Lt(lt=1.0), TuneSpec(low=0.1, high=0.99, step=None, log=False, categories=None, tunable=True)] = 0.55, k: Annotated[float, Ge(ge=0.0), TuneSpec(low=0.5, high=20.0, step=None, log=False, categories=None, tunable=True)] = 3.0, deviation_gain: Annotated[float, Gt(gt=0.0), TuneSpec(low=1.0, high=2.0, step=None, log=False, categories=None, tunable=True)] = 1.5, cutoff: Annotated[float, Gt(gt=0.0), Lt(lt=1.0), TuneSpec(low=0.3, high=0.7, step=None, log=False, categories=None, tunable=True)] = 0.5, g: Annotated[float, Gt(gt=0.0), TuneSpec(low=2.0, high=20.0, step=None, log=False, categories=None, tunable=True)] = 10.0, noise_method: Annotated[float, TuneSpec(low=None, high=None, step=None, log=False, categories=None, tunable=False)] = -1.0, output: Literal['pc', 'orientation', 'feature_type'] = 'pc', norm: Literal['clip', 'rescale'] | None = 'clip')[source]#

Bases: NormalizedOutputMixin, FocusEdge

Enhance colony edges using colour phase congruency across three channels.

Runs FocusEdgeMonogenicPhase’s monogenic chain independently on each of three colour channels, then fuses the results. Phase congruency is already invariant to illumination level; fusing across colour additionally lets a channel with amplitude but no phase agreement – pigment speckle, agar grain, Bayer demosaic noise – veto an edge the luminance channel would otherwise assert.

Best For:

Filamentous plates. This is where the measured benefit lives. Under lateral chromatic aberration on load_synth_filamentous_plate, fusion="joint" localizes boundaries to 1.008 px against FocusEdgeMonogenicPhase’s 1.158 px, and its error is flat in the aberration.
Plates where agar texture produces spurious luminance edges that carry no matching chromatic structure, so an incoherent chroma channel can veto them.

Consider Also:

FocusEdgeMonogenicPhase on round-colony plates. Measured: on load_synth_yeast_plate under the same aberration it beats every fusion mode (1.143 px, against joint 1.375, coherent 1.700, l2 1.776). On round colonies, colour buys nothing under chromatic aberration.
FocusEdgeMonogenicPhase when the plate is near-achromatic, which this operation rejects outright.
FocusEdgePhase when you also want corner strength from the moment tensor.

Parameters:

color_space (Literal['lab', 'hsv']) – "lab" (default) or "hsv". Channels are taken in luminance-first order: lab gives (L*, a*, b*), hsv gives (V, H, S). Raw CIELAB is already the perceptual common scale – CIE76’s dE*ab is the Euclidean norm over raw L*a*b* – so no per-axis rescaling is applied; dividing by nominal axis ranges would corrupt an already-normalized space and bias against chroma by 128/100.
fusion (Literal['joint', 'coherent', 'l2']) – "joint" (default) shares one denominator across channels, so incoherent chroma amplitude vetoes a spurious luminance edge. "l2" is CMPCM’s rule – three independent congruencies combined by root-sum-of-squares – and has no cross-channel interaction whatsoever. "coherent" sums the monogenic vectors before taking their norm; it cancels opposite-phase responses, including a genuine anti-correlated chromatic edge where lightness falls as yellowness rises. Opt-in, never default.
chroma_weight_1 (Annotated[float, Ge(ge=0.0), TuneSpec(low=0.0, high=8.0, step=None, log=False, categories=None, tunable=True)]) – Weight on the first chromatic axis (a* under lab, H under hsv). Luminance is pinned at 1.0, so there are two degrees of freedom, not three. At 0.0 the axis is switched off entirely and, with chroma_weight_2 also 0.0, the operation reduces bit-for-bit to FocusEdgeMonogenicPhase on the luminance channel.
chroma_weight_2 (Annotated[float, Ge(ge=0.0), TuneSpec(low=0.0, high=8.0, step=None, log=False, categories=None, tunable=True)]) – Weight on the second chromatic axis (b* / S). The search bound of 8.0 brackets “chroma off” through “chroma dominates” for the axis that carries signal on real plates – b* reaches parity with L* at 2.6 (Rhodotorula) and 4.4 (Neurospora) – and deliberately refuses to let a* reach parity, which needs 19 to 61.
lift (Literal['monogenic', 'conformal']) – "monogenic" (default). "conformal" raises NotImplementedError at construction – the field exists so the surface is stable, but the path is gated on an experiment it may well fail.
n_scale (Annotated[int, Ge(ge=2), TuneSpec(low=3, high=6, step=None, log=False, categories=None, tunable=True)]) – Number of log-Gabor scales. Must be at least 2; the frequency-spread weight divides by n_scale - 1.
min_wavelength (Annotated[float, Ge(ge=2.0), TuneSpec(low=2.0, high=10.0, step=None, log=False, categories=None, tunable=True)]) – Wavelength of the finest scale, in pixels.
mult (Annotated[float, Gt(gt=1.0), TuneSpec(low=1.5, high=3.0, step=None, log=False, categories=None, tunable=True)]) – Wavelength multiplier between successive scales.
sigma_onf (Annotated[float, Ge(ge=0.1), Lt(lt=1.0), TuneSpec(low=0.1, high=0.99, step=None, log=False, categories=None, tunable=True)]) – Ratio of each filter’s Gaussian sigma to its centre frequency. Strictly below 1.0: at exactly 1.0 the log-Gabor’s Gaussian width is log(1.0) = 0 and the filter bank divides by zero.
k (Annotated[float, Ge(ge=0.0), TuneSpec(low=0.5, high=20.0, step=None, log=False, categories=None, tunable=True)]) – Noise standard deviations above the mean at which the threshold sits. phasecongmono’s default is 3.0, not FocusEdgePhase’s 2.0.
deviation_gain (Annotated[float, Gt(gt=0.0), TuneSpec(low=1.0, high=2.0, step=None, log=False, categories=None, tunable=True)]) – Scales the phase-deviation term. Kovesi: “sensible values are from 1 to about 2.”
cutoff (Annotated[float, Gt(gt=0.0), Lt(lt=1.0), TuneSpec(low=0.3, high=0.7, step=None, log=False, categories=None, tunable=True)]) – Fractional frequency-spread below which the response is penalized.
g (Annotated[float, Gt(gt=0.0), TuneSpec(low=2.0, high=20.0, step=None, log=False, categories=None, tunable=True)]) – Sharpness of the frequency-spread sigmoid.
noise_method (Annotated[float, TuneSpec(low=None, high=None, step=None, log=False, categories=None, tunable=False)]) – -1 estimates the Rayleigh parameter from the median of the finest scale’s amplitude; -2 uses its histogram mode; any value >= 0 is the threshold verbatim, so 0.0 disables it.
output (Literal['pc', 'orientation', 'feature_type']) – Response map to write to detect_mat. "pc" is the fused congruency; "orientation" and "feature_type" are normalized from radians into [0, 1] by (theta + pi/2) / pi. The two angle maps are diagnostic for "joint" and "l2": their weighted fused vector does not directly produce those modes’ scalar PC response. They are most meaningful where PC is high.
norm (Literal['clip', 'rescale'] | None) – Output-range policy for output="pc". "clip" (default) saturates to [0, 1], "rescale" remaps the observed PC range to [0, 1], and None preserves it. norm does not affect angle maps, whose fixed [0, 1] encoding would otherwise lose its physical meaning.

Returns:

Input image with detect_mat replaced by the selected response map. PC output follows norm; angle outputs retain their normalized [0, 1] encoding. rgb and gray are unchanged.

Return type:

Image

Raises:

NotImplementedError – If lift="conformal", at construction time.
ValueError – If the image is achromatic – all three RGB channels identical – since a* and b* are then identically zero and joint degenerates to a luminance congruency divided by itself. Raised inside _operate, so ImageOperation.apply() wraps it; walk the __cause__ chain to catch it.
ValidationError – On any out-of-range field.

Note

This operation reads ``image.rgb``, not ``detect_mat``. It is a pipeline source, like SetDetectMode: any enhancer placed before it in an ImagePipeline has no effect on its output. Colour phase congruency is defined on colour, and rgb is not a supported detect_mat layer. This is legal under @validate_operation_integrity, which forbids mutating rgb and gray and says nothing about reading them.

Warning

Colour is not free, and on round colonies it is not even useful. The chromatic-aberration experiment behind this operation (docs/superpowers/plans/2026-07-09-focus-edge-color-phase/experiments/) measured boundary localization under a radial R/B misregistration. On the filamentous plate fusion="joint" wins. On the yeast plate, plain FocusEdgeMonogenicPhase on luminance beats all three fusion modes at every aberration level. Lateral CA creates chromatic edges, and joint asserts them coherently – so its detected edge follows the displaced chroma rather than merging it, and its error grows five times faster than luminance-only’s. Reach for this operation when the structure you want is filamentous, not merely because the plate is coloured.

Warning

color_space="hsv" band-passes raw hue across its wrap discontinuity. Hue is circular on [0, 1), so a log-Gabor filter sees a unit step at the 0.99 -> 0.01 seam where the colour is in fact continuous, and a near-red boundary manufactures a phantom edge. We do not unwrap, because the CMPCM paper does not and ("hsv", "l2") is the configuration its ranking regression reproduces. Prefer the "lab" default, which has no seam.

Examples

Fuse three channels of a synthetic yeast plate. The output is a congruency map in [0, 1], like every other FocusEdge:

>>> from phenotypic.data import load_synth_yeast_plate
>>> from phenotypic.enhance import FocusEdgeColorPhase
>>> enhanced = FocusEdgeColorPhase().apply(load_synth_yeast_plate())
>>> bool(0.0 <= enhanced.detect_mat[:].min() <= enhanced.detect_mat[:].max() <= 1.0)
True

Switch chroma off and recover the luminance-only monogenic port exactly:

>>> luminance_only = FocusEdgeColorPhase(chroma_weight_1=0.0, chroma_weight_2=0.0)
>>> bool(luminance_only.apply(load_synth_yeast_plate()).detect_mat[:].max() > 0.5)
True

See also

FocusEdgeMonogenicPhase, which this reduces to when both chroma weights are 0.0.

Methods

`__init__`	Create a new model by parsing and validating input data from keyword arguments.
`apply`	Applies the operation to an image, either in-place or on a copy.
`construct`
`copy`	Returns a copy of the model.
`dict`
`from_json`	Reconstruct an operation from JSON written by `to_json()`.
`from_orm`
`json`
`model_construct`	Creates a new instance of the Model class with validated data.
`model_copy`	!!! abstract "Usage Documentation"
`model_dump`	!!! abstract "Usage Documentation"
`model_dump_json`	!!! abstract "Usage Documentation"
`model_json_schema`	Generates a JSON schema for a model class.
`model_parametrized_name`	Compute the class name for parametrizations of generic classes.
`model_post_init`	Initialize logging and memory tracking after model construction.
`model_rebuild`	Try to rebuild the pydantic-core schema for the model.
`model_validate`	Validate a pydantic model instance.
`model_validate_json`	!!! abstract "Usage Documentation"
`model_validate_strings`	Validate the given object with string data against the Pydantic model.
`parse_file`
`parse_obj`
`parse_raw`
`schema`
`schema_json`
`to_json`	Serialize this operation to JSON.
`update_forward_refs`
`validate`
`widget`	Return (and optionally display) the root widget.

Attributes

`model_computed_fields`
`model_config`	Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].
`model_extra`	Get extra fields set during validation.
`model_fields`
`model_fields_set`	Returns the set of fields that have been explicitly set on this model instance.
`color_space`
`fusion`
`chroma_weight_1`
`chroma_weight_2`
`lift`
`n_scale`
`min_wavelength`
`mult`
`sigma_onf`
`k`
`deviation_gain`
`cutoff`
`g`
`noise_method`
`output`
`norm`

color_space: ColorSpaceName#

fusion: PhaseFusion#

chroma_weight_1: Annotated[float, TuneSpec(0.0, 8.0)]#

chroma_weight_2: Annotated[float, TuneSpec(0.0, 8.0)]#

lift: PhaseLift#

n_scale: Annotated[int, TuneSpec(3, 6)]#

min_wavelength: Annotated[float, TuneSpec(2.0, 10.0)]#

mult: Annotated[float, TuneSpec(1.5, 3.0)]#

sigma_onf: Annotated[float, TuneSpec(0.1, 0.99)]#

k: Annotated[float, TuneSpec(0.5, 20.0)]#

deviation_gain: Annotated[float, TuneSpec(1.0, 2.0)]#

cutoff: Annotated[float, TuneSpec(0.3, 0.7)]#

g: Annotated[float, TuneSpec(2.0, 20.0)]#

noise_method: Annotated[float, TuneSpec(tunable=False)]#

output: ColorPhaseOutput#

__copy__() → Self#

Returns a shallow copy of the model.

Return type:: Self

__deepcopy__(memo: dict[int, Any] | None = None) → Self#

Returns a deep copy of the model.

Parameters:: memo (dict[int, Any] | None)
Return type:: Self

__del__()#: Automatically stop tracemalloc when the object is deleted.

classmethod __get_pydantic_json_schema__(core_schema: CoreSchema, handler: GetJsonSchemaHandler, /) → JsonSchemaValue#

Hook into generating the model’s JSON schema.

Parameters:

core_schema (CoreSchema) – A pydantic-core CoreSchema. You can ignore this argument and call the handler with a new CoreSchema, wrap this CoreSchema ({‘type’: ‘nullable’, ‘schema’: current_schema}), or just call the handler with the original schema.
handler (GetJsonSchemaHandler) – Call into Pydantic’s internal JSON schema generation. This will raise a pydantic.errors.PydanticInvalidForJsonSchema if JSON schema generation fails. Since this gets called by BaseModel.model_json_schema you can override the schema_generator argument to that function to change JSON schema generation globally for a type.

Returns:

A JSON schema, as a Python object.

Return type:

JsonSchemaValue

__init__(**data: Any) → None#

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:: data (Any)
Return type:: None

__iter__() → Generator[tuple[str, Any], None, None]#

So dict(model) works.

Return type:: Generator[tuple[str, Any], None, None]

__pretty__(fmt: Callable[[Any], Any], **kwargs: Any) → Generator[Any]#

Used by devtools (https://python-devtools.helpmanual.io/) to pretty print objects.

Parameters:

fmt (Callable[[Any], Any])
kwargs (Any)

Return type:

Generator[Any]

classmethod __pydantic_init_subclass__(**kwargs: Any) → None#

Move norm to the end of the subclass’s field order.

Parameters:: kwargs (Any)
Return type:: None

classmethod __pydantic_on_complete__() → None#

This is called once the class and its fields are fully initialized and ready to be used.

This typically happens when the class is created (just before [__pydantic_init_subclass__()][pydantic.main.BaseModel.__pydantic_init_subclass__] is called on the superclass), except when forward annotations are used that could not immediately be resolved. In that case, it will be called later, when the model is rebuilt automatically or explicitly using [model_rebuild()][pydantic.main.BaseModel.model_rebuild].

Return type:: None

__repr_name__() → str#

Name of the instance’s class, used in __repr__.

Return type:: str

__repr_recursion__(object: Any) → str#

Returns the string representation of a recursive object.

Parameters:: object (Any)
Return type:: str

__rich_repr__() → RichReprResult#

Used by Rich (https://rich.readthedocs.io/en/stable/pretty.html) to pretty print objects.

Return type:: RichReprResult

apply(image, inplace=False)#

Applies the operation to an image, either in-place or on a copy.

Parameters:

image (Image) – The arr image to apply the operation on.
inplace (bool) – If True, modifies the image in place; otherwise, operates on a copy of the image.

Returns:

The modified image after applying the operation.

Return type:

Image

classmethod construct(_fields_set: set[str] | None = None, **values: Any) → Self#

Parameters:

_fields_set (set[str] | None)
values (Any)

Return type:

Self

Returns a copy of the model.

!!! warning “Deprecated”: This method is now deprecated; use model_copy instead.

If you need include or exclude, use:

`python {test="skip" lint="skip"} data = self.model_dump(include=include, exclude=exclude, round_trip=True) data = {**data, **(update or {})} copied = self.model_validate(data) `

Parameters:

include (AbstractSetIntStr | MappingIntStrAny | None) – Optional set or mapping specifying which fields to include in the copied model.
exclude (AbstractSetIntStr | MappingIntStrAny | None) – Optional set or mapping specifying which fields to exclude in the copied model.
update (Dict[str, Any] | None) – Optional dictionary of field-value pairs to override field values in the copied model.
deep (bool) – If True, the values of fields that are Pydantic models will be deep-copied.

Returns:

A copy of the model with included, excluded and updated fields as specified.

Return type:

Self

Parameters:

include (set[int] | set[str] | Mapping[int, set[int] | set[str] | Mapping[int, IncEx | bool] | Mapping[str, IncEx | bool] | bool] | Mapping[str, set[int] | set[str] | Mapping[int, IncEx | bool] | Mapping[str, IncEx | bool] | bool] | None)
exclude (set[int] | set[str] | Mapping[int, set[int] | set[str] | Mapping[int, IncEx | bool] | Mapping[str, IncEx | bool] | bool] | Mapping[str, set[int] | set[str] | Mapping[int, IncEx | bool] | Mapping[str, IncEx | bool] | bool] | None)
by_alias (bool)
exclude_unset (bool)
exclude_defaults (bool)
exclude_none (bool)

Return type:

Dict[str, Any]

classmethod from_json(json_data: str | Path | dict) → BaseOperation#

Reconstruct an operation from JSON written by to_json().

Accepts a JSON string, a path to a JSON file, or a pre-parsed envelope dict (same input handling as ImagePipeline.from_json()). Polymorphic: ImageOperation.from_json(path) returns whatever concrete operation the file holds. When called on a narrower subclass, the resolved class must be a subclass of it, else a TypeError is raised.

Parameters:

json_data (str | Path | dict) – A JSON string, path to a JSON file, or envelope dict.

Returns:

The reconstructed operation instance.

Raises:

AttributeError – If the recorded class cannot be resolved in the phenotypic namespace.
TypeError – If called on a concrete subclass and the file holds a class that is not a subclass of it.

Return type:

BaseOperation

Example

>>> import tempfile
>>> from pathlib import Path
>>> from phenotypic.abc_ import ImageOperation
>>> from phenotypic.detect import OtsuDetector
>>> with tempfile.TemporaryDirectory() as d:
...     p = Path(d) / "op.json"
...     OtsuDetector().to_json(p)
...     loaded = ImageOperation.from_json(p)  # polymorphic
>>> type(loaded).__name__
'OtsuDetector'

classmethod from_orm(obj: Any) → Self#

Parameters:: obj (Any)
Return type:: Self

Parameters:

include (set[int] | set[str] | Mapping[int, set[int] | set[str] | Mapping[int, IncEx | bool] | Mapping[str, IncEx | bool] | bool] | Mapping[str, set[int] | set[str] | Mapping[int, IncEx | bool] | Mapping[str, IncEx | bool] | bool] | None)
exclude (set[int] | set[str] | Mapping[int, set[int] | set[str] | Mapping[int, IncEx | bool] | Mapping[str, IncEx | bool] | bool] | Mapping[str, set[int] | set[str] | Mapping[int, IncEx | bool] | Mapping[str, IncEx | bool] | bool] | None)
by_alias (bool)
exclude_unset (bool)
exclude_defaults (bool)
exclude_none (bool)
encoder (Callable[[Any], Any] | None)
models_as_dict (bool)
dumps_kwargs (Any)

Return type:

str

model_computed_fields = {}#

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True, 'extra': 'forbid', 'validate_assignment': True}#: Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

classmethod model_construct(_fields_set: set[str] | None = None, **values: Any) → Self#

Creates a new instance of the Model class with validated data.

Creates a new model setting __dict__ and __pydantic_fields_set__ from trusted or pre-validated data. Default values are respected, but no other validation is performed.

!!! note: model_construct() generally respects the model_config.extra setting on the provided model. That is, if model_config.extra == ‘allow’, then all extra passed values are added to the model instance’s __dict__ and __pydantic_extra__ fields. If model_config.extra == ‘ignore’ (the default), then all extra passed values are ignored. Because no validation is performed with a call to model_construct(), having model_config.extra == ‘forbid’ does not result in an error if extra values are passed, but they will be ignored.

Parameters:

_fields_set (set[str] | None) – A set of field names that were originally explicitly set during instantiation. If provided, this is directly used for the [model_fields_set][pydantic.BaseModel.model_fields_set] attribute. Otherwise, the field names from the values argument will be used.
values (Any) – Trusted or pre-validated data dictionary.

Returns:

A new instance of the Model class with validated data.

Return type:

Self

model_copy(*, update: Mapping[str, Any] | None = None, deep: bool = False) → Self#

!!! abstract “Usage Documentation”: [model_copy](../concepts/models.md#model-copy)

Returns a copy of the model.

!!! note: The underlying instance’s [__dict__][object.__dict__] attribute is copied. This might have unexpected side effects if you store anything in it, on top of the model fields (e.g. the value of [cached properties][functools.cached_property]).

Parameters:

update (Mapping[str, Any] | None) – Values to change/add in the new model. Note: the data is not validated before creating the new model. You should trust this data.
deep (bool) – Set to True to make a deep copy of the model.

Returns:

New model instance.

Return type:

Self

!!! abstract “Usage Documentation”: [model_dump](../concepts/serialization.md#python-mode)

Generate a dictionary representation of the model, optionally specifying which fields to include or exclude.

Parameters:

mode (Literal['json', 'python'] | str) – The mode in which to_python should run. If mode is ‘json’, the output will only contain JSON serializable types. If mode is ‘python’, the output may contain non-JSON-serializable Python objects.
include (set[int] | set[str] | Mapping[int, set[int] | set[str] | Mapping[int, IncEx | bool] | Mapping[str, IncEx | bool] | bool] | Mapping[str, set[int] | set[str] | Mapping[int, IncEx | bool] | Mapping[str, IncEx | bool] | bool] | None) – A set of fields to include in the output.
exclude (set[int] | set[str] | Mapping[int, set[int] | set[str] | Mapping[int, IncEx | bool] | Mapping[str, IncEx | bool] | bool] | Mapping[str, set[int] | set[str] | Mapping[int, IncEx | bool] | Mapping[str, IncEx | bool] | bool] | None) – A set of fields to exclude from the output.
context (Any | None) – Additional context to pass to the serializer.
by_alias (bool | None) – Whether to use the field’s alias in the dictionary key if defined.
exclude_unset (bool) – Whether to exclude fields that have not been explicitly set.
exclude_defaults (bool) – Whether to exclude fields that are set to their default value.
exclude_none (bool) – Whether to exclude fields that have a value of None.
exclude_computed_fields (bool) – Whether to exclude computed fields. While this can be useful for round-tripping, it is usually recommended to use the dedicated round_trip parameter instead.
round_trip (bool) – If True, dumped values should be valid as input for non-idempotent types such as Json[T].
warnings (bool | Literal['none', 'warn', 'error']) – How to handle serialization errors. False/”none” ignores them, True/”warn” logs errors, “error” raises a [PydanticSerializationError][pydantic_core.PydanticSerializationError].
fallback (Callable[[Any], Any] | None) – A function to call when an unknown value is encountered. If not provided, a [PydanticSerializationError][pydantic_core.PydanticSerializationError] error is raised.
serialize_as_any (bool) – Whether to serialize fields with duck-typing serialization behavior.

Returns:

A dictionary representation of the model.

Return type:

dict[str, Any]

!!! abstract “Usage Documentation”: [model_dump_json](../concepts/serialization.md#json-mode)

Generates a JSON representation of the model using Pydantic’s to_json method.

Parameters:

indent (int | None) – Indentation to use in the JSON output. If None is passed, the output will be compact.
ensure_ascii (bool) – If True, the output is guaranteed to have all incoming non-ASCII characters escaped. If False (the default), these characters will be output as-is.
include (set[int] | set[str] | Mapping[int, set[int] | set[str] | Mapping[int, IncEx | bool] | Mapping[str, IncEx | bool] | bool] | Mapping[str, set[int] | set[str] | Mapping[int, IncEx | bool] | Mapping[str, IncEx | bool] | bool] | None) – Field(s) to include in the JSON output.
exclude (set[int] | set[str] | Mapping[int, set[int] | set[str] | Mapping[int, IncEx | bool] | Mapping[str, IncEx | bool] | bool] | Mapping[str, set[int] | set[str] | Mapping[int, IncEx | bool] | Mapping[str, IncEx | bool] | bool] | None) – Field(s) to exclude from the JSON output.
context (Any | None) – Additional context to pass to the serializer.
by_alias (bool | None) – Whether to serialize using field aliases.
exclude_unset (bool) – Whether to exclude fields that have not been explicitly set.
exclude_defaults (bool) – Whether to exclude fields that are set to their default value.
exclude_none (bool) – Whether to exclude fields that have a value of None.
exclude_computed_fields (bool) – Whether to exclude computed fields. While this can be useful for round-tripping, it is usually recommended to use the dedicated round_trip parameter instead.
round_trip (bool) – If True, dumped values should be valid as input for non-idempotent types such as Json[T].
warnings (bool | Literal['none', 'warn', 'error']) – How to handle serialization errors. False/”none” ignores them, True/”warn” logs errors, “error” raises a [PydanticSerializationError][pydantic_core.PydanticSerializationError].
fallback (Callable[[Any], Any] | None) – A function to call when an unknown value is encountered. If not provided, a [PydanticSerializationError][pydantic_core.PydanticSerializationError] error is raised.
serialize_as_any (bool) – Whether to serialize fields with duck-typing serialization behavior.

Returns:

A JSON string representation of the model.

Return type:

str

property model_extra: dict[str, Any] | None#

Get extra fields set during validation.

Returns:: A dictionary of extra fields, or None if config.extra is not set to “allow”.

model_fields = {'chroma_weight_1': FieldInfo(annotation=float, required=False, default=1.0, description='Weight on the first chromatic axis (``a*`` under ``lab``, ``H`` under ``hsv``). Luminance is pinned at ``1.0``, so there are two degrees of freedom, not three. At ``0.0`` the axis is switched off entirely and, with ``chroma_weight_2`` also ``0.0``, the operation reduces **bit-for-bit** to :class:`FocusEdgeMonogenicPhase` on the luminance channel.', metadata=[Ge(ge=0.0), TuneSpec(low=0.0, high=8.0, step=None, log=False, categories=None, tunable=True)]), 'chroma_weight_2': FieldInfo(annotation=float, required=False, default=1.0, description='Weight on the second chromatic axis (``b*`` / ``S``). The search bound of ``8.0`` brackets "chroma off" through "chroma dominates" for the axis that carries signal on real plates -- ``b*`` reaches parity with ``L*`` at ``2.6`` (Rhodotorula) and ``4.4`` (Neurospora) -- and deliberately refuses to let ``a*`` reach parity, which needs ``19`` to ``61``.', metadata=[Ge(ge=0.0), TuneSpec(low=0.0, high=8.0, step=None, log=False, categories=None, tunable=True)]), 'color_space': FieldInfo(annotation=Literal['lab', 'hsv'], required=False, default='lab', description='``"lab"`` (default) or ``"hsv"``. Channels are taken in **luminance-first** order: ``lab`` gives ``(L*, a*, b*)``, ``hsv`` gives ``(V, H, S)``. Raw CIELAB is already the perceptual common scale -- CIE76\'s ``dE*ab`` is the Euclidean norm over raw ``L*a*b*`` -- so no per-axis rescaling is applied; dividing by nominal axis ranges would corrupt an already-normalized space and bias against chroma by ``128/100``.'), 'cutoff': FieldInfo(annotation=float, required=False, default=0.5, description='Fractional frequency-spread below which the response is penalized.', metadata=[Gt(gt=0.0), Lt(lt=1.0), TuneSpec(low=0.3, high=0.7, step=None, log=False, categories=None, tunable=True)]), 'deviation_gain': FieldInfo(annotation=float, required=False, default=1.5, description='Scales the phase-deviation term. Kovesi: "sensible values are from 1 to about 2."', metadata=[Gt(gt=0.0), TuneSpec(low=1.0, high=2.0, step=None, log=False, categories=None, tunable=True)]), 'fusion': FieldInfo(annotation=Literal['joint', 'coherent', 'l2'], required=False, default='joint', description='``"joint"`` (default) shares one denominator across channels, so incoherent chroma amplitude vetoes a spurious luminance edge. ``"l2"`` is CMPCM\'s rule -- three independent congruencies combined by root-sum-of-squares -- and has **no** cross-channel interaction whatsoever. ``"coherent"`` sums the monogenic vectors before taking their norm; it cancels opposite-phase responses, **including a genuine anti-correlated chromatic edge** where lightness falls as yellowness rises. Opt-in, never default.'), 'g': FieldInfo(annotation=float, required=False, default=10.0, description='Sharpness of the frequency-spread sigmoid.', metadata=[Gt(gt=0.0), TuneSpec(low=2.0, high=20.0, step=None, log=False, categories=None, tunable=True)]), 'k': FieldInfo(annotation=float, required=False, default=3.0, description="Noise standard deviations above the mean at which the threshold sits. ``phasecongmono``'s default is ``3.0``, not :class:`FocusEdgePhase`'s ``2.0``.", metadata=[Ge(ge=0.0), TuneSpec(low=0.5, high=20.0, step=None, log=False, categories=None, tunable=True)]), 'lift': FieldInfo(annotation=Literal['monogenic', 'conformal'], required=False, default='monogenic', description='``"monogenic"`` (default). ``"conformal"`` raises :exc:`NotImplementedError` **at construction** -- the field exists so the surface is stable, but the path is gated on an experiment it may well fail.'), 'min_wavelength': FieldInfo(annotation=float, required=False, default=3.0, description='Wavelength of the finest scale, in pixels.', metadata=[Ge(ge=2.0), TuneSpec(low=2.0, high=10.0, step=None, log=False, categories=None, tunable=True)]), 'mult': FieldInfo(annotation=float, required=False, default=2.1, description='Wavelength multiplier between successive scales.', metadata=[Gt(gt=1.0), TuneSpec(low=1.5, high=3.0, step=None, log=False, categories=None, tunable=True)]), 'n_scale': FieldInfo(annotation=int, required=False, default=4, description='Number of log-Gabor scales. Must be at least 2; the frequency-spread weight divides by ``n_scale - 1``.', metadata=[Ge(ge=2), TuneSpec(low=3, high=6, step=None, log=False, categories=None, tunable=True)]), 'noise_method': FieldInfo(annotation=float, required=False, default=-1.0, description="``-1`` estimates the Rayleigh parameter from the median of the finest scale's amplitude; ``-2`` uses its histogram mode; any value ``>= 0`` is the threshold verbatim, so ``0.0`` disables it.", metadata=[TuneSpec(low=None, high=None, step=None, log=False, categories=None, tunable=False)]), 'norm': FieldInfo(annotation=Union[Literal['clip', 'rescale'], NoneType], required=False, default='clip', description='Output-range policy for ``output="pc"``. ``"clip"`` (default) saturates to [0, 1], ``"rescale"`` remaps the observed PC range to [0, 1], and ``None`` preserves it. ``norm`` does not affect angle maps, whose fixed [0, 1] encoding would otherwise lose its physical meaning.'), 'output': FieldInfo(annotation=Literal['pc', 'orientation', 'feature_type'], required=False, default='pc', description='Response map to write to ``detect_mat``. ``"pc"`` is the fused congruency; ``"orientation"`` and ``"feature_type"`` are normalized from radians into [0, 1] by ``(theta + pi/2) / pi``. The two angle maps are diagnostic for ``"joint"`` and ``"l2"``: their weighted fused vector does not directly produce those modes\' scalar PC response. They are most meaningful where PC is high.'), 'sigma_onf': FieldInfo(annotation=float, required=False, default=0.55, description="Ratio of each filter's Gaussian sigma to its centre frequency. Strictly below ``1.0``: at exactly ``1.0`` the log-Gabor's Gaussian width is ``log(1.0) = 0`` and the filter bank divides by zero.", metadata=[Ge(ge=0.1), Lt(lt=1.0), TuneSpec(low=0.1, high=0.99, step=None, log=False, categories=None, tunable=True)])}#

property model_fields_set: set[str]#

Returns the set of fields that have been explicitly set on this model instance.

Returns:

A set of strings representing the fields that have been set,: i.e. that were not filled from defaults.

classmethod model_json_schema(by_alias: bool = True, ref_template: str = '#/$defs/{model}', schema_generator: type[~pydantic.json_schema.GenerateJsonSchema] = <class 'pydantic.json_schema.GenerateJsonSchema'>, mode: ~typing.Literal['validation', 'serialization'] = 'validation', *, union_format: ~typing.Literal['any_of', 'primitive_type_array'] = 'any_of') → dict[str, Any]#

Generates a JSON schema for a model class.

Parameters:

by_alias (bool) – Whether to use attribute aliases or not.
ref_template (str) – The reference template.
union_format (Literal['any_of', 'primitive_type_array']) –
The format to use when combining schemas from unions together. Can be one of:
- ’any_of’: Use the [anyOf](https://json-schema.org/understanding-json-schema/reference/combining#anyOf)
keyword to combine schemas (the default). - ‘primitive_type_array’: Use the [type](https://json-schema.org/understanding-json-schema/reference/type) keyword as an array of strings, containing each type of the combination. If any of the schemas is not a primitive type (string, boolean, null, integer or number) or contains constraints/metadata, falls back to any_of.
schema_generator (type[GenerateJsonSchema]) – To override the logic used to generate the JSON schema, as a subclass of GenerateJsonSchema with your desired modifications
mode (Literal['validation', 'serialization']) – The mode in which to generate the schema.

Returns:

The JSON schema for the given model class.

Return type:

dict[str, Any]

classmethod model_parametrized_name(params: tuple[type[Any], ...]) → str#

Compute the class name for parametrizations of generic classes.

This method can be overridden to achieve a custom naming scheme for generic BaseModels.

Parameters:: params (tuple[type[Any], ...]) – Tuple of types of the class. Given a generic class Model with 2 type variables and a concrete model Model[str, int], the value (str, int) would be passed to params.
Returns:: String representing the new class where params are passed to cls as type variables.
Raises:: TypeError – Raised when trying to generate concrete names for non-generic models.
Return type:: str

model_post_init(_BaseOperation__context: Any) → None#

Initialize logging and memory tracking after model construction.

Replaces the legacy __init__ body: creates the per-class logger and, when that logger is enabled for INFO level or higher, starts tracemalloc so per-operation memory usage can be logged.

Parameters:

__context – Pydantic post-init context (unused).
_BaseOperation__context (Any)

Return type:

None

classmethod model_rebuild(*, force: bool = False, raise_errors: bool = True, _parent_namespace_depth: int = 2, _types_namespace: MappingNamespace | None = None) → bool | None#

Try to rebuild the pydantic-core schema for the model.

This may be necessary when one of the annotations is a ForwardRef which could not be resolved during the initial attempt to build the schema, and automatic rebuilding fails.

Parameters:

force (bool) – Whether to force the rebuilding of the model schema, defaults to False.
raise_errors (bool) – Whether to raise errors, defaults to True.
_parent_namespace_depth (int) – The depth level of the parent namespace, defaults to 2.
_types_namespace (MappingNamespace | None) – The types namespace, defaults to None.

Returns:

Returns None if the schema is already “complete” and rebuilding was not required. If rebuilding _was_ required, returns True if rebuilding was successful, otherwise False.

Return type:

bool | None

Validate a pydantic model instance.

Parameters:

obj (Any) – The object to validate.
strict (bool | None) – Whether to enforce types strictly.
extra (Literal['allow', 'ignore', 'forbid'] | None) – Whether to ignore, allow, or forbid extra data during model validation. See the [extra configuration value][pydantic.ConfigDict.extra] for details.
from_attributes (bool | None) – Whether to extract data from object attributes.
context (Any | None) – Additional context to pass to the validator.
by_alias (bool | None) – Whether to use the field’s alias when validating against the provided input data.
by_name (bool | None) – Whether to use the field’s name when validating against the provided input data.

Raises:

ValidationError – If the object could not be validated.

Returns:

The validated model instance.

Return type:

Self

!!! abstract “Usage Documentation”: [JSON Parsing](../concepts/json.md#json-parsing)

Validate the given JSON data against the Pydantic model.

Parameters:

json_data (str | bytes | bytearray) – The JSON data to validate.
strict (bool | None) – Whether to enforce types strictly.
extra (Literal['allow', 'ignore', 'forbid'] | None) – Whether to ignore, allow, or forbid extra data during model validation. See the [extra configuration value][pydantic.ConfigDict.extra] for details.
context (Any | None) – Extra variables to pass to the validator.
by_alias (bool | None) – Whether to use the field’s alias when validating against the provided input data.
by_name (bool | None) – Whether to use the field’s name when validating against the provided input data.

Returns:

The validated Pydantic model.

Raises:

ValidationError – If json_data is not a JSON string or the object could not be validated.

Return type:

Self

Validate the given object with string data against the Pydantic model.

Parameters:

obj (Any) – The object containing string data to validate.
strict (bool | None) – Whether to enforce types strictly.
extra (Literal['allow', 'ignore', 'forbid'] | None) – Whether to ignore, allow, or forbid extra data during model validation. See the [extra configuration value][pydantic.ConfigDict.extra] for details.
context (Any | None) – Extra variables to pass to the validator.
by_alias (bool | None) – Whether to use the field’s alias when validating against the provided input data.
by_name (bool | None) – Whether to use the field’s name when validating against the provided input data.

Returns:

The validated Pydantic model.

Return type:

Self

classmethod parse_file(path: str | Path, *, content_type: str | None = None, encoding: str = 'utf8', proto: DeprecatedParseProtocol | None = None, allow_pickle: bool = False) → Self#

Parameters:

path (str | Path)
content_type (str | None)
encoding (str)
proto (DeprecatedParseProtocol | None)
allow_pickle (bool)

Return type:

Self

classmethod parse_obj(obj: Any) → Self#

Parameters:: obj (Any)
Return type:: Self

classmethod parse_raw(b: str | bytes, *, content_type: str | None = None, encoding: str = 'utf8', proto: DeprecatedParseProtocol | None = None, allow_pickle: bool = False) → Self#

Parameters:

b (str | bytes)
content_type (str | None)
encoding (str)
proto (DeprecatedParseProtocol | None)
allow_pickle (bool)

Return type:

Self

classmethod schema(by_alias: bool = True, ref_template: str = '#/$defs/{model}') → Dict[str, Any]#

Parameters:

by_alias (bool)
ref_template (str)

Return type:

Dict[str, Any]

classmethod schema_json(*, by_alias: bool = True, ref_template: str = '#/$defs/{model}', **dumps_kwargs: Any) → str#

Parameters:

by_alias (bool)
ref_template (str)
dumps_kwargs (Any)

Return type:

str

to_json(filepath: str | Path | None = None) → str | None#

Serialize this operation to JSON.

Captures the operation as a {"class", "params"} envelope: params is model_dump(mode="json") (every declared field, including nested operations and raw arrays; PrivateAttr state such as loggers and timing is excluded automatically), and class records the concrete class name so from_json() can rebuild the right subclass. This mirrors ImagePipeline.to_json().

Parameters:: filepath (str | Path | None) – Optional path to write the JSON to. When None, the JSON string is returned instead. Accepts a str or Path.
Returns:: The JSON string when filepath is None, otherwise None.
Return type:: str | None

Example

>>> import tempfile
>>> from pathlib import Path
>>> from phenotypic.detect import OtsuDetector
>>> from phenotypic.sdk_ import CONFIG_SUFFIX_OPERATION, ensure_typed_json_suffix
>>> with tempfile.TemporaryDirectory() as d:
...     p = Path(d) / "op.json"
...     saved = ensure_typed_json_suffix(p, CONFIG_SUFFIX_OPERATION)
...     OtsuDetector(ignore_zeros=True).to_json(p)
...     loaded = OtsuDetector.from_json(saved)
>>> loaded.ignore_zeros
True

classmethod update_forward_refs(**localns: Any) → None#

Parameters:: localns (Any)
Return type:: None

classmethod validate(value: Any) → Self#

Parameters:: value (Any)
Return type:: Self

widget(image: Image | None = None, show: bool = False) → Widget#

Return (and optionally display) the root widget.

Parameters:

image (Image | None) – Optional image to visualize. If provided, visualization controls will be added to the widget.
show (bool) – Whether to display the widget immediately. Defaults to False.

Returns:

The root widget.

Return type:

ipywidgets.Widget

Raises:

ImportError – If ipywidgets or IPython are not installed.

norm: NormOut#

phenotypic.enhance.FocusEdgeColorPhase#

This Page