o &?e^L@sdZddlZddlZddlmZddlmZddlm Z ddl m Z m Z m Z  dd d Zdd dZdddZddZ    dddZdS)z) Methods to characterize image textures. N)check_nD)gray2rgb) img_as_float) _glcm_loop_local_binary_pattern_multiblock_lbpFc CsRt|dt|ddt|ddt|}|}t|jtjr&td|jtjtj fvr7|dur7tdt|jtj rJt |dkrJtd |durPd }||krXtd tj|tj d }tj|tj d }tj ||t|t|ftjd d}t||||||rt|d}||}|r|tj }tj|ddd} d| | dk<|| }|S)a|Calculate the gray-level co-occurrence matrix. A gray level co-occurrence matrix is a histogram of co-occurring grayscale values at a given offset over an image. .. versionchanged:: 0.19 `greymatrix` was renamed to `graymatrix` in 0.19. Parameters ---------- image : array_like Integer typed input image. Only positive valued images are supported. If type is other than uint8, the argument `levels` needs to be set. distances : array_like List of pixel pair distance offsets. angles : array_like List of pixel pair angles in radians. levels : int, optional The input image should contain integers in [0, `levels`-1], where levels indicate the number of gray-levels counted (typically 256 for an 8-bit image). This argument is required for 16-bit images or higher and is typically the maximum of the image. As the output matrix is at least `levels` x `levels`, it might be preferable to use binning of the input image rather than large values for `levels`. symmetric : bool, optional If True, the output matrix `P[:, :, d, theta]` is symmetric. This is accomplished by ignoring the order of value pairs, so both (i, j) and (j, i) are accumulated when (i, j) is encountered for a given offset. The default is False. normed : bool, optional If True, normalize each matrix `P[:, :, d, theta]` by dividing by the total number of accumulated co-occurrences for the given offset. The elements of the resulting matrix sum to 1. The default is False. Returns ------- P : 4-D ndarray The gray-level co-occurrence histogram. The value `P[i,j,d,theta]` is the number of times that gray-level `j` occurs at a distance `d` and at an angle `theta` from gray-level `i`. If `normed` is `False`, the output is of type uint32, otherwise it is float64. The dimensions are: levels x levels x number of distances x number of angles. References ---------- .. [1] M. Hall-Beyer, 2007. GLCM Texture: A Tutorial https://prism.ucalgary.ca/handle/1880/51900 DOI:`10.11575/PRISM/33280` .. [2] R.M. Haralick, K. Shanmugam, and I. Dinstein, "Textural features for image classification", IEEE Transactions on Systems, Man, and Cybernetics, vol. SMC-3, no. 6, pp. 610-621, Nov. 1973. :DOI:`10.1109/TSMC.1973.4309314` .. [3] M. Nadler and E.P. Smith, Pattern Recognition Engineering, Wiley-Interscience, 1993. .. [4] Wikipedia, https://en.wikipedia.org/wiki/Co-occurrence_matrix Examples -------- Compute 2 GLCMs: One for a 1-pixel offset to the right, and one for a 1-pixel offset upwards. >>> image = np.array([[0, 0, 1, 1], ... [0, 0, 1, 1], ... [0, 2, 2, 2], ... [2, 2, 3, 3]], dtype=np.uint8) >>> result = graycomatrix(image, [1], [0, np.pi/4, np.pi/2, 3*np.pi/4], ... levels=4) >>> result[:, :, 0, 0] array([[2, 2, 1, 0], [0, 2, 0, 0], [0, 0, 3, 1], [0, 0, 0, 1]], dtype=uint32) >>> result[:, :, 0, 1] array([[1, 1, 3, 0], [0, 1, 1, 0], [0, 0, 0, 2], [0, 0, 0, 0]], dtype=uint32) >>> result[:, :, 0, 2] array([[3, 0, 2, 0], [0, 2, 2, 0], [0, 0, 1, 2], [0, 0, 0, 0]], dtype=uint32) >>> result[:, :, 0, 3] array([[2, 0, 0, 0], [1, 1, 2, 0], [0, 0, 2, 1], [0, 0, 0, 0]], dtype=uint32) rr distancesanglesz^Float images are not supported by graycomatrix. Convert the image to an unsigned integer type.Nz{The levels argument is required for data types other than uint8. The resulting matrix will be at least levels ** 2 in size.rz)Negative-valued images are not supported.zUThe maximum grayscale value in the image should be smaller than the number of levels.dtypeC)rorder)rrrrrTaxisZkeepdims)rnpascontiguousarraymax issubdtyperfloating ValueErrorZuint8Zint8Z signedintegeranyfloat64zeroslenZuint32rZ transposeastypesum) imager r ZlevelsZ symmetricZnormedZ image_maxPZPt glcm_sumsr$X/home/www/facesmatcher.com/pyenv/lib/python3.10/site-packages/skimage/feature/texture.py graycomatrixs< _      r&contrastcCst|dd|j\}}}}||krtd|dkrtd|dkr%td|tj}tj|ddd }d ||dk<||}tjd|d|f\}}|d krU||d } n'|d krat||} n|dkrpdd||d } n |dvrunt|d|dkrtj|d dd} t | } | S|dkrtj|d dd} | S|dkr(tj ||ftjd} t t | |d d d f}t t | d |d d f}|tj||dd} |tj||dd} t tj|| d dd}t tj|| d dd}tj|| | dd}|dk}d||dk<d | |<|}||||||| |<| S|dvr?| ||d d f} tj|| dd} | S)a Calculate texture properties of a GLCM. Compute a feature of a gray level co-occurrence matrix to serve as a compact summary of the matrix. The properties are computed as follows: - 'contrast': :math:`\sum_{i,j=0}^{levels-1} P_{i,j}(i-j)^2` - 'dissimilarity': :math:`\sum_{i,j=0}^{levels-1}P_{i,j}|i-j|` - 'homogeneity': :math:`\sum_{i,j=0}^{levels-1}\frac{P_{i,j}}{1+(i-j)^2}` - 'ASM': :math:`\sum_{i,j=0}^{levels-1} P_{i,j}^2` - 'energy': :math:`\sqrt{ASM}` - 'correlation': .. math:: \sum_{i,j=0}^{levels-1} P_{i,j}\left[\frac{(i-\mu_i) \ (j-\mu_j)}{\sqrt{(\sigma_i^2)(\sigma_j^2)}}\right] Each GLCM is normalized to have a sum of 1 before the computation of texture properties. .. versionchanged:: 0.19 `greycoprops` was renamed to `graycoprops` in 0.19. Parameters ---------- P : ndarray Input array. `P` is the gray-level co-occurrence histogram for which to compute the specified property. The value `P[i,j,d,theta]` is the number of times that gray-level j occurs at a distance d and at an angle theta from gray-level i. prop : {'contrast', 'dissimilarity', 'homogeneity', 'energy', 'correlation', 'ASM'}, optional The property of the GLCM to compute. The default is 'contrast'. Returns ------- results : 2-D ndarray 2-dimensional array. `results[d, a]` is the property 'prop' for the d'th distance and the a'th angle. References ---------- .. [1] M. Hall-Beyer, 2007. GLCM Texture: A Tutorial v. 1.0 through 3.0. The GLCM Tutorial Home Page, https://prism.ucalgary.ca/handle/1880/51900 DOI:`10.11575/PRISM/33280` Examples -------- Compute the contrast for GLCMs with distances [1, 2] and angles [0 degrees, 90 degrees] >>> image = np.array([[0, 0, 1, 1], ... [0, 0, 1, 1], ... [0, 2, 2, 2], ... [2, 2, 3, 3]], dtype=np.uint8) >>> g = graycomatrix(image, [1, 2], [0, np.pi/2], levels=4, ... normed=True, symmetric=True) >>> contrast = graycoprops(g, 'contrast') >>> contrast array([[0.58333333, 1. ], [1.25 , 2.75 ]]) r"z'num_level and num_level2 must be equal.rznum_dist must be positive.znum_angle must be positive.rTrrr'r dissimilarity homogeneityg?)ASMenergy correlationz is an invalid propertyr,)rr+r-r gV瞯<)r'r)r*)rshaperrrrr ZogridabssqrtrarrayrangeZreshape)r"propZ num_levelZ num_level2Znum_distZ num_angler#IJweightsasmresultsZdiff_iZdiff_jZstd_iZstd_jZcovZmask_0Zmask_1r$r$r% graycopropss` @      r9defaultcCsrt|dtdtdtdtdtdd}t|jtjr$tdtj|tj d }t ||||| }|S) aS Compute the local binary patterns (LBP) of an image. LBP is a visual descriptor often used in texture classification. Parameters ---------- image : (M, N) array 2D grayscale image. P : int Number of circularly symmetric neighbor set points (quantization of the angular space). R : float Radius of circle (spatial resolution of the operator). method : str {'default', 'ror', 'uniform', 'nri_uniform', 'var'}, optional Method to determine the pattern: ``default`` Original local binary pattern which is grayscale invariant but not rotation invariant. ``ror`` Extension of default pattern which is grayscale invariant and rotation invariant. ``uniform`` Uniform pattern which is grayscale invariant and rotation invariant, offering finer quantization of the angular space. For details, see [1]_. ``nri_uniform`` Variant of uniform pattern which is grayscale invariant but not rotation invariant. For details, see [2]_ and [3]_. ``var`` Variance of local image texture (related to contrast) which is rotation invariant but not grayscale invariant. Returns ------- output : (M, N) array LBP image. References ---------- .. [1] T. Ojala, M. Pietikainen, T. Maenpaa, "Multiresolution gray-scale and rotation invariant texture classification with local binary patterns", IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 7, pp. 971-987, July 2002 :DOI:`10.1109/TPAMI.2002.1017623` .. [2] T. Ahonen, A. Hadid and M. Pietikainen. "Face recognition with local binary patterns", in Proc. Eighth European Conf. Computer Vision, Prague, Czech Republic, May 11-14, 2004, pp. 469-481, 2004. http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.214.6851 :DOI:`10.1007/978-3-540-24670-1_36` .. [3] T. Ahonen, A. Hadid and M. Pietikainen, "Face Description with Local Binary Patterns: Application to Face Recognition", IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 28, no. 12, pp. 2037-2041, Dec. 2006 :DOI:`10.1109/TPAMI.2006.244` rDRUNV)r:ZroruniformZ nri_uniformvarzApplying `local_binary_pattern` to floating-point images may give unexpected results when small numerical differences between adjacent pixels are present. It is recommended to use this function with images of integer dtype.r ) rordrrrrwarningswarnrrrlower)r!r"r<methodmethodsoutputr$r$r%local_binary_patterns 9rIcCs$tj|tjd}t|||||}|S)aMulti-block local binary pattern (MB-LBP). The features are calculated similarly to local binary patterns (LBPs), (See :py:meth:`local_binary_pattern`) except that summed blocks are used instead of individual pixel values. MB-LBP is an extension of LBP that can be computed on multiple scales in constant time using the integral image. Nine equally-sized rectangles are used to compute a feature. For each rectangle, the sum of the pixel intensities is computed. Comparisons of these sums to that of the central rectangle determine the feature, similarly to LBP. Parameters ---------- int_image : (N, M) array Integral image. r : int Row-coordinate of top left corner of a rectangle containing feature. c : int Column-coordinate of top left corner of a rectangle containing feature. width : int Width of one of the 9 equal rectangles that will be used to compute a feature. height : int Height of one of the 9 equal rectangles that will be used to compute a feature. Returns ------- output : int 8-bit MB-LBP feature descriptor. References ---------- .. [1] L. Zhang, R. Chu, S. Xiang, S. Liao, S.Z. Li. "Face Detection Based on Multi-Block LBP Representation", In Proceedings: Advances in Biometrics, International Conference, ICB 2007, Seoul, Korea. http://www.cbsr.ia.ac.cn/users/scliao/papers/Zhang-ICB07-MBLBP.pdf :DOI:`10.1007/978-3-540-74549-5_2` r )rrZfloat32r )Z int_imagercwidthheightlbp_coder$r$r%multiblock_lbpks*rOrrrrgGz?gQ??c Csjtj|tjd}tj|tjd}t|} t|jdkr t|} t| } d} t| } | dddf|9<| dddf|9<||} ||} t | D]c\} }|\}}| |}| |}|dd| >@}|rd|| ||||||f||}|| ||||||f<qOd|| ||||||f||}|| ||||||f<qO| S)aMulti-block local binary pattern visualization. Blocks with higher sums are colored with alpha-blended white rectangles, whereas blocks with lower sums are colored alpha-blended cyan. Colors and the `alpha` parameter can be changed. Parameters ---------- image : ndarray of float or uint Image on which to visualize the pattern. r : int Row-coordinate of top left corner of a rectangle containing feature. c : int Column-coordinate of top left corner of a rectangle containing feature. width : int Width of one of 9 equal rectangles that will be used to compute a feature. height : int Height of one of 9 equal rectangles that will be used to compute a feature. lbp_code : int The descriptor of feature to visualize. If not provided, the descriptor with 0 value will be used. color_greater_block : tuple of 3 floats Floats specifying the color for the block that has greater intensity value. They should be in the range [0, 1]. Corresponding values define (R, G, B) values. Default value is white (1, 1, 1). color_greater_block : tuple of 3 floats Floats specifying the color for the block that has greater intensity value. They should be in the range [0, 1]. Corresponding values define (R, G, B) values. Default value is cyan (0, 0.69, 0.96). alpha : float Value in the range [0, 1] that specifies opacity of visualization. 1 - fully transparent, 0 - opaque. Returns ------- output : ndarray of float Image with MB-LBP visualization. References ---------- .. [1] L. Zhang, R. Chu, S. Xiang, S. Liao, S.Z. Li. "Face Detection Based on Multi-Block LBP Representation", In Proceedings: Advances in Biometrics, International Conference, ICB 2007, Seoul, Korea. http://www.cbsr.ia.ac.cn/users/scliao/papers/Zhang-ICB07-MBLBP.pdf :DOI:`10.1007/978-3-540-74549-5_2` r r))rS)rSr)rSrr)rr)rr)rrS)rrSNrr) rZasarrayrcopyrr.rrr1 enumerate)r!rJrKrLrMrNZcolor_greater_blockZcolor_less_blockalpharHZneighbor_rect_offsetsZcentral_rect_rZcentral_rect_cZ element_numoffsetZoffset_rZoffset_cZcurr_rZcurr_cZhas_greater_value new_valuer$r$r%draw_multiblock_lbps>;  rZ)NFF)r')r:)rrPrQrR)__doc__rCnumpyrZ _shared.utilsrcolorrutilrZ_texturerrr r&r9rIrOrZr$r$r$r%s&      }M0