[;jrR~dZddlZddlZddlmZddlmZddlm Z ddl m Z m Z m Z dd Zdd Zdd Zd Z dd Zy)z) Methods to characterize image textures. N)check_nD)gray2rgb) img_as_float) _glcm_loop_local_binary_pattern_multiblock_lbpc:t|dt|ddt|ddtj|}|j}tj|j tj r td|j tjtjfvr | tdtj|j tjr#tj|dkr td|d }||k\r td tj|tj }tj|tj }tj||t|t|ftjd }t!||||||rtj"|d}||z}|rD|j%tj}tj&|dd} d| | dk(<|| z}|S)aCalculate 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 4 GLCMs using 1-pixel distance and 4 different angles. For example, an angle of 0 radians refers to the neighboring pixel to the right; pi/4 radians to the top-right diagonal neighbor; pi/2 radians to the pixel above, and so forth. >>> 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.z{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)rrrrrTaxiskeepdims)rnpascontiguousarraymax issubdtyperfloating ValueErroruint8int8 signedintegeranyfloat64zeroslenuint32r transposeastypesum) imager r levels symmetricnormed image_maxPPt glcm_sumss `G:\00. PROJECTS\API\Inventory\templateJSON\kerjaOCR\Lib\site-packages\skimage/feature/texture.py graycomatrixr2s@ UA Y;' VQ!   'E I }}U[["++. =   {{288RWW--&. )   }}U[[""2"23uqy8IDEE ~F 1  $$YbjjAI  ! !& ;F  YV5RYYc A ui3 \\!\ * F HHRZZ FF16D9 $% )q.! Y Hcfd}tddj\}}}|k7r td|dkr td|dkr tdjtj t j dd }d ||dk(<|ztjddf\}}|d k(r ||z d z} nE|dk(rt j||z } n'|dk(rdd||z d zzz } n|dvrnt|d|dk(r1t j d zd} t j| } | S|dk(rt j d zd} | S|dk(r |\} } | S|dk(r,|\}} t j || z d zzd} | S|dk(rA|\}} t j || z d zzd}t j|} | S|dk(rKt jdk7t j }t j |zd} | S|dk(rkt j||ftj } t jtjd d d f}t jtjd d d f}|t j |zdz }|t j |zdz }t jt j |d zzd}t jt j |d zzd}t j ||zzd}|dk}d ||dk<d | |<|}||||||zz | |<| S|dvr/ jd d f} t j | zd}  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] - 'mean': :math:`\sum_{i=0}^{levels-1} i*P_{i}` - 'variance': :math:`\sum_{i=0}^{levels-1} P_{i}*(i-mean)^2` - 'std': :math:`\sqrt{variance}` - 'entropy': :math:`\sum_{i,j=0}^{levels-1} -P_{i,j}*log(P_{i,j})` 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', 'mean', 'variance', 'std', 'entropy'}, 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 ]]) ctjjdddf}tj|zd}||fS)Nrrr)rarangereshaper()Imeanr. num_levels r1 glcm_meanzgraycoprops..glcm_meansB IIi ( ()Q1)= >vva!e&)$wr3r.z'num_level and num_level2 must be equal.rznum_dist must be positive.znum_angle must be positive.rTrrcontrastr dissimilarity homogeneityg?)ASMenergy correlationentropyvariancer:stdz is an invalid propertyrBr6rAr:rErFrD)whereoutrCrgV瞯<)r>r?r@)rshaperr'rr"r(ogridabssqrtlog zeros_liker#arrayranger8)r.propr< num_level2num_dist num_angler0r9Jweightsasmresults_r:varlndiff_idiff_jstd_istd_jcovmask_0mask_1r;s` @r1 graycopropsrcsJ  Q334770Y HiJBCC1}566A~677 Aqv5I !Ii1nNA 88AiK9, -DAq zq5Q,  &&Q-  A!|+, W W D6!89:: xffQT'''#,N NM &&AF+J NI [ 7F NE  +4&&q4xAo.V<@ N? +4ffQ1t8/*8''#,8 N7  ffQqAvBMM!,<= =&&Rf-2 N/  ((Hi0 C HHU9% & . . 1a/C D HHU9% & . .9a/C DRVVAE//RVVAE//qFq=0v>?qFq=0v>?ffQ&6/*8 $uu}f+vv)FG N = =//9iA">?&&W62 Nr3ct|dtdtdtdtdtdd}tj|jtj rt jdtj|tj }t|||||j}|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)defaultroruniform nri_uniformrZzApplying `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) rordrrrrwarningswarnrr"r lower)r)r.rfmethodmethodsoutputs r1local_binary_patternru>sr UAs83xs83x3x G }}U[["++.  5  bjj 9E "5!Q 0G HF Mr3cntj|tj}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)rrfloat32r ) int_imagercwidthheightlbp_codes r1multiblock_lbpr~s2T$$YbjjAIy!Qv>H Or3c tj|tj}tj|tj}tj|} t |j dkr t |} t| } d} tj| } | dddfxx|zcc<| dddfxx|zcc<||z} ||z} t| D]~\} }|\}}| |z}| |z}|dd| z zz}|r/d|z | |||z|||zfz||zz}|| |||z|||zf<Qd|z | |||z|||zfz||zz}|| |||z|||zf<| 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` rr))r)rr)rrr)rr)rr)rr)rrNrr) rasarrayr"copyr$rIrrrO enumerate)r)ryrzr{r|r}color_greater_blockcolor_less_blockalphartneighbor_rect_offsetscentral_rect_rcentral_rect_c element_numoffsetoffset_roffset_ccurr_rcurr_chas_greater_value new_values r1draw_multiblock_lbprs@**%8 Kzz"2"**EWWU^F 5;;!%& !F HH%:;!Q$6)!Q$5(ZNYN()>? V#((*(*$a+o(>? Uf&(&6E>*AA'++,IIRF6FVO+Vfun-DD EUf&(&6E>*AA'(()IIRF6FVO+Vfun-DD E% @( Mr3)NFF)r>)rj)r)rrr)rgGz?gQ?g?)__doc__ronumpyr _shared.utilsrcolorrutilr_texturerr r r2rcrur~rr3r1rsP$HHX vQhK\,j!$ wr3