o 'jg@sNdZddlZddlZddlmZddlmZddlZddZ GdddZ dS) z This code is refer from: https://github.com/open-mmlab/mmocr/blob/main/mmocr/datasets/pipelines/textdet_targets/fcenet_targets.py N)fftnormcCs(t|dksJt|d|ddS)Nr:0yE>)lenabs)Zvecr g/var/www/html/Deteccion_Ine/venv/lib/python3.10/site-packages/paddleocr/ppocr/data/imaug/fce_targets.py vector_slopesr cseZdZdZ      d.fdd Zd d Zd d ZddZddZddZ ddZ d/ddZ ddZ ddZ ddZdd Zd!d"Zd#d$Zd%efd&d'Zd(d)Zd*d+Zd,d-ZZS)0 FCENetTargetsaGenerate the ground truth targets of FCENet: Fourier Contour Embedding for Arbitrary-Shaped Text Detection. [https://arxiv.org/abs/2104.10442] Args: fourier_degree (int): The maximum Fourier transform degree k. resample_step (float): The step size for resampling the text center line (TCL). It's better not to exceed half of the minimum width. center_region_shrink_ratio (float): The shrink ratio of text center region. level_size_divisors (tuple(int)): The downsample ratio on each level. level_proportion_range (tuple(tuple(int))): The range of text sizes assigned to each level. @333333? )rg?)g?g?)g??@c sbtt|ts Jt|tsJt|t|ksJ||_||_||_||_||_ ||_ dSN) super__init__ isinstancetuplerfourier_degree resample_stepcenter_region_shrink_ratiolevel_size_divisorslevel_proportion_rangeorientation_thr)selfrrrr r!r"kwargs __class__r r r0s  zFCENetTargets.__init__cCs|jdkr|t|dddd}n |t|ddd}|jdkr0|t|dddd}n |t|ddd}tttj||ddddS)NrZaxisrr'rgr)ndimrreshapenpZarccosZclipsum)r#Zvec1Zvec2Z unit_vec1Z unit_vec2r r r vector_angleEs  zFCENetTargets.vector_anglecsnjdksJjddksJjddksJt|ts J|dks&JfddttdD}t|}tdg|}|t |d}d}dg}td|D]S} | |} |dt|kr| ||dkr|d7}|dt|kr| ||dksk| ||} |t|krn| ||} ||d|| } | | qU| dt |}|S) aResample n points on a line. Args: line (ndarray): The points composing a line. n (int): The resampled points number. Returns: resampled_line (ndarray): The points composing the resampled line. rrrc$g|]}t|d|qSrr.0iliner r csz/FCENetTargets.resample_line..grr') r*shaperintrangerr-r,Zcumsumfloatappendarray)r#r5nZ length_list total_lengthZ length_cumsumZ delta_lengthZcurrent_edge_indZresampled_liner3Zcurrent_line_lenZcurrent_edge_end_shiftZend_shift_ratioZ current_pointr r4r resample_lineRsZ       zFCENetTargets.resample_linec Cs|jdksJ|jddksJ|jddksJ|||j\}}||||}}t||g}|ddkr>t||d<||d|d}||d|dt|}tj|ddtj|dd} | ddkrp||} } n||} } ||| | fS)aGet the respective points composing head edge, tail edge, top sideline and bottom sideline. Args: points (ndarray): The points composing a text polygon. Returns: head_edge (ndarray): The two points composing the head edge of text polygon. tail_edge (ndarray): The two points composing the tail edge of text polygon. top_sideline (ndarray): The points composing top curved sideline of text polygon. bot_sideline (ndarray): The points composing bottom curved sideline of text polygon. rrrr()r*r7find_head_tailr"r,vstackrmean) r#points head_inds tail_indsZ head_edgeZ tail_edge pad_points sideline1 sideline2Zsideline_mean_shiftZ top_sidelineZ bot_sideliner r r reorder_poly_edges*      zFCENetTargets.reorder_poly_edgec"s|jdksJ|jddksJ|jddksJt|ts Jt|dkrt||dg}|dd|ddg}g}tD]4\}}fdd|d|dfD}|} t| || } | | d| d} | | | | qDt |tj } t |tj } tj |dd }tt|dd|dd t|dd|dd }|t|}tt}d | d | }|d |7}t|ddkr|t|ddd7<|dd7<|d |7}t||g}tt|t|df}tt|dtt|d}dtdtj d tt|d d d d}|t|}tt|D]}||||d|t|d|d||ddf<q8t||j\}}||dt|}|dt|}|dt|}||kr||}}||}}||g}||g}||fSt|d|dt|d|dt|d|dt|d|dkrddgddgg}ddgddgg}nddgddgg}ddgddgg}t||dd||ddt||dd||dd} t||dd||ddt||dd||dd}!| |!|kr=|d}|d}||fS|d}|d}||fS)aFind the head edge and tail edge of a text polygon. Args: points (ndarray): The points composing a text polygon. orientation_thr (float): The threshold for distinguishing between head edge and tail edge among the horizontal and vertical edges of a quadrangle. Returns: head_inds (list): The indexes of two points composing head edge. tail_inds (list): The indexes of two points composing tail edge. rrr@rNr'csg|]}|tqSr )r)r2xZedge_vecr r r6sz0FCENetTargets.find_head_tail..r(?g333333?gffffff?g?rrr)r*r7rr:rr,rB enumerater-r.r;r<pirCmaximumrmaxzeros concatenateZarangesqrtexppowerr9Z unravel_indexZargmaxr )"r#rDr"rGZ theta_sumZadjacent_vec_thetar3Z edge_vec1Z adjacent_indZadjacent_edge_vecZtemp_theta_sumZtemp_adjacent_thetaZtheta_sum_scoreZadjacent_theta_scoreZ poly_centerZ edge_distZ dist_scoreZposition_scoreZscoreZ pad_scoreZ score_matrixrKZgaussianZ head_startZtail_incrementZ tail_startZhead_endZtail_endrErFZhorizontal_edge_indsZvertical_edge_indsZvertical_len_sumZhorizontal_len_sumr rLr rAs      "          zFCENetTargets.find_head_tailc sjjkr dksJJjdjdkr!dks$JJjddks-Jjddks6Jt|ts=JtfddttdD}tfddttdD}||d}ttt||d}| |}| |} || fS)aResample two sidelines to be of the same points number according to step size. Args: sideline1 (ndarray): The points composing a sideline of a text polygon. sideline2 (ndarray): The points composing another sideline of a text polygon. resample_step (float): The resampled step size. Returns: resampled_line1 (ndarray): The resampled line 1. resampled_line2 (ndarray): The resampled line 2. rrrcr/r0rr1)rHr r r6&z4FCENetTargets.resample_sidelines..cr/r0rr1)rIr r r6*rX) r*r7rr:r-r9rrRr8r?) r#rHrIrZlength1Zlength2r>Zresample_point_numZresampled_line1Zresampled_line2r )rHrIr resample_sideliness (     z FCENetTargets.resample_sidelinescCst|tsJ|\}}t||ftj}g}|D]}|dd}||\} } } } || | |j\} } | ddd} t | t | krCq| | d}t | d| dd}t | d| dd}t ||j}t ||j}t |||dkr||t ||}| |t | |} | |t | |} t dt |dD]\}||| ||||j }||d| |d||d|j }||d| |d||d|j }||| ||||j }t||||gtj}||qqt||d|S)aGenerate text center region mask. Args: img_size (tuple): The image size of (height, width). text_polys (list[list[ndarray]]): The list of text polygons. Returns: center_region_mask (ndarray): The text center region mask. r'rNrrr)rrr,rSuint8r+rJrYrrrr8r9rrBastypeint32r;cv2fillPoly)r#img_size text_polyshwZcenter_region_maskZcenter_region_boxespolyZpolygon_points_Ztop_lineZbot_lineZresampled_top_lineZresampled_bot_lineZ center_lineZline_head_shrink_lenZline_tail_shrink_lenZhead_shrink_numZtail_shrink_numr3tltrbrblZcurrent_center_boxr r r generate_center_region_mask7s        z)FCENetTargets.generate_center_region_maskcCs0g}tt|D]2}||}|t|dkr|d}n||d}||d|dd|d|dddqt|}t||d|}|tj}g} tt|D]:}||} ||}|t|dkro|d}n||d}| dkrzqX||| } t| D] } || | } | | qqXt| S)a Resample one polygon with n points on its boundary. Args: polygon (list[float]): The input polygon. n (int): The number of resampled points. Returns: resampled_polygon (list[float]): The resampled polygon. rrrrMr)r9rr;r-r,r<r[r\)r#polygonr=lengthr3p1Zp2r>Zn_on_each_line new_polygonnumZdxdyjpointr r r resample_polygonus2   4        zFCENetTargets.resample_polygonc Cs||jdd}t|dddf}|dddf}t|}t||dd}||}t||d|d|g}|S)zNormalize one polygon so that its start point is at right most. Args: polygon (list[float]): The origin polygon. Returns: new_polygon (lost[float]): The polygon with start point at right. rr(Nrr)rCr,r ZargsortZargminrT) r#rkZ temp_polygonrKyZindex_xZindex_yindexrnr r r normalize_polygons zFCENetTargets.normalize_polygoncCs\|dddf|dddfd}t|t|}t|| d|d|df}|S)a*Perform Fourier transformation to generate Fourier coefficients ck from polygon. Args: polygon (ndarray): An input polygon. fourier_degree (int): The maximum Fourier degree K. Returns: c (ndarray(complex)): Fourier coefficients. Nrry?)rrr,hstack)r#rkrrDZc_fftcr r r poly2fouriers$ $zFCENetTargets.poly2fouriercCst||dt||dkr|St||dt||dkr-|dddSt||dt||dkrA|S|dddS)aMake sure the polygon reconstructed from Fourier coefficients c in the clockwise direction. Args: polygon (list[float]): The origin polygon. Returns: new_polygon (lost[float]): The polygon in clockwise point order. rNr'r)r,r )r#rwrr r r clockwises$ $$zFCENetTargets.clockwisecCs^||}||}|||}|||}t|d}t|d}t||g}|S)agCalculate Fourier signature from input polygon. Args: polygon (ndarray): The input polygon. fourier_degree (int): The maximum Fourier degree K. Returns: fourier_signature (ndarray): An array shaped (2k+1, 2) containing real part and image part of 2k+1 Fourier coefficients. r)) rrrurxryr,realr+imagrv)r#rkrZresampled_polygon fourier_coeffZ real_partZ image_partZfourier_signaturer r r cal_fourier_signatures   z#FCENetTargets.cal_fourier_signaturec Cst|tsJ|\}}|j}tj|dd||ftjd}tj|dd||ftjd}|D]}tj||ftjd} t|d} t | | tj d| | d|} t| |dD]} | dkr| | | |dfd| || |ddddf|| |ddddf<| | | |dfd| || |ddddf|| |ddddf<q]t| dk} tjt| tjd|}| dddf| dddf}}| |df|||||f<| |df|||||f<q]q.||fS)aGenerate Fourier coefficient maps. Args: img_size (tuple): The image size of (height, width). text_polys (list[list[ndarray]]): The list of text polygons. Returns: fourier_real_map (ndarray): The Fourier coefficient real part maps. fourier_image_map (ndarray): The Fourier coefficient image part maps. rrZdtyperr'rrNrM)rrrr,rSZfloat32rZr<r+r]r^r[r\r}r9ZargwhereonesrZint64)r#r_r`rarbkZreal_mapZimag_maprcmaskrkr|r3ZyxZk_indrsrKr r r generate_fourier_mapss2 " z#FCENetTargets.generate_fourier_mapscCs\t|tsJ|\}}tj||ftjd}|D]}tj|tjdd}t ||dq|S)a,Generate text center region mask and geometry attribute maps. Args: img_size (tuple): The image size (height, width). text_polys (list[list[ndarray]]): The list of text polygons. Returns: text_region_mask (ndarray): The text region mask. r~rr) rrr,rSrZr<r\r+r]r^)r#r_r`rarbZtext_region_maskrcrkr r r generate_text_region_masks z'FCENetTargets.generate_text_region_mask mask_sizecCsJtj|tjd}|D]}|ddtjddd}t||dq |S)a_Generate effective mask by setting the ineffective regions to 0 and effective regions to 1. Args: mask_size (tuple): The mask size. polygons_ignore (list[[ndarray]]: The list of ignored text polygons. Returns: mask (ndarray): The effective mask of (height, width). r~r'rrr)r,rrZr+r[r\r]r^)r#rZpolygons_ignorerrcinstancer r r generate_effective_mask&s  z%FCENetTargets.generate_effective_maskcCs|\}}|j}|j}ddtt|D}ddtt|D} g} |D]C} tj| tjdd} t | \} } }}t |||d}t |D]\}}|d|krY|dkrfnqG|| | ||qGq$|D]C}tj|tjdd} t | \} } }}t |||d}t |D]\}}|d|kr|dkrnq| | |||qqjt |D]W\}}g}||||f}| |||d }| |||||d }| |||| |d }| |||||\}}| || || t|q| S) avGenerate ground truth target on each level. Args: img_size (list[int]): Shape of input image. text_polys (list[list[ndarray]]): A list of ground truth polygons. ignore_polys (list[list[ndarray]]): A list of ignored polygons. Returns: level_maps (list(ndarray)): A list of ground target on each level. cSg|]}gqSr r r1r r r r6Hz8FCENetTargets.generate_level_targets..cSrr r r1r r r r6Irr~rrrrN)r r!r9rr,r<r\r+r]Z boundingRectrRrOr;rrirrrT)r#r_r`Z ignore_polysrarbZ lv_size_divsZlv_proportion_rangeZ lv_text_polysZlv_ignore_polys level_mapsrcrkrdZbox_wZbox_hZ proportionindZproportion_rangeZ ignore_polyZ size_divisorZcurrent_level_mapsZlevel_img_sizeZ text_regionZ center_regionZeffective_maskZfourier_real_mapZfourier_image_mapsr r r generate_level_targets;sh        z$FCENetTargets.generate_level_targetscCst|tsJ|d}|d}|d}|j\}}}g}g} t||D]\} } | dur0| | q"|| q"|||f|| } | d| d| dd} | D]\}}|||<qO|S) zGenerate the ground truth targets for FCENet. Args: results (dict): The input result dictionary. Returns: results (dict): The output result dictionary. imageZpolys ignore_tagsTrrr)Zp3_mapsZp4_mapsZp5_maps)rdictr7zipr;ritems)r#resultsrZpolygonsrrarbrdZ polygon_masksZpolygon_masks_ignoretagrkrmappingkeyvaluer r r generate_targetsvs*      zFCENetTargets.generate_targetscCs||}|Sr)r)r#rr r r __call__s zFCENetTargets.__call__)rrrrrr)rj)__name__ __module__ __qualname____doc__rr.r?rJrArYrirrrurxryr}rrrrrrr __classcell__r r r%r r s4 3)b' >*(;%r ) rr]numpyr,Z numpy.fftrZ numpy.linalgrsysr r r r r r s