SIFTCV Class Reference

Uses sift features to establish similarity. More...

Inheritance diagram for SIFTCV:

Collaboration diagram for SIFTCV:

Public Member Functions
def	__init__ (self, theParams=CfgSIFTCV())
	Constructor for the puzzle piece sift class. More...
def	compare (self, piece_A, piece_B, tauMatch=None)
	Compare between two passed puzzle piece data. More...
def	extractFeature (self, piece)
	Compute SIFT features from the raw puzzle data. More...
def	score (self, piece_A, piece_B)
	Compute the score between two passed puzzle piece data. More...
def	solveMatchedPuzzle (self, puzzle, sol)
Public Member Functions inherited from MatchSimilar
def	compare (self, piece_A, piece_B)

Additional Inherited Members
Public Attributes inherited from Matcher
	params

Detailed Description

Uses sift features to establish similarity.

Constructor & Destructor Documentation

__init__()

def __init__	(		self,
			theParams = CfgSIFTCV()
	)

Constructor for the puzzle piece sift class.

Reimplemented from MatchSimilar.

Member Function Documentation

compare()

def compare	(		self,
			piece_A,
			piece_B,
			tauMatch = None
	)

Compare between two passed puzzle piece data.

Note that this code has additional calculations that estimate the transformation that will register or align the puzzle pieces.

See references for idea behind this comparison:

https://opencv24-python-tutorials.readthedocs.io/en/latest/py_tutorials/py_feature2d/py_matcher/py_matcher.html and https://scikit-image.org/docs/dev/auto_examples/transform/plot_matching.html

Todo:

Establish whether the registration code should be here or elsewhere. The reason for being here is that it takes advantage of matching computations made to prevent additional computations.

Yet, these are done whether it is a match or not. Better to not bother if not even a match. Going to go with that by rearranging the code [2023/11/03]. Delete note if acceptable.

Parameters

[in]	piece_A	Template instance saving a piece's info.
[in]	piece_B	Template instance saving a piece's info.
[out]	Comparison	result & rotation angle(degree) & other params.

extractFeature()

def extractFeature	(		self,
			piece
	)

Compute SIFT features from the raw puzzle data.

This function just extracts the SIFT features from the piece information. The calling scope needs to deal with the feature storage and matching part.

Parameters

[in]

piece

Puzzle piece to use.

Returns

(kp, des) Image patch keypoints and SIFT descriptors.

Reimplemented from Matcher.

score()

def score	(		self,
			piece_A,
			piece_B
	)

Compute the score between two passed puzzle piece data.

Parameters

[in]	piece_A	Template instance saving a piece's info.
[in]	piece_B	Template instance saving a piece's info.
[out]	Distance	of the feature vectors. (Overload if not proper).

Reimplemented from Matcher.

solveMatchedPuzzle()

def solveMatchedPuzzle	(		self,
			puzzle,
			sol
	)

Reimplemented from Matcher.

---

The documentation for this class was generated from the following file:

• /home/pvela/python/puzzle_solver/puzzle/pieces/matchSimilar.py