œ,jI(SSKrSSKrSSKJrJrJrJr SSKJr SSK J r SSK J r SSK Jr SSKJr S S jrg) N)arctan2exppisqrt)draw) img_as_float)gaussian)check_nD)gray2rgbc [USS5 [U5nURn Ub)Ub&[U5S- [U5:wa [ S5eUb[U5nUSnUb[U5S- nUc/[ U5V s/sHoU S--[ SU-5- PM nn Uc,[ U5V s/sHoU S--[ U5- PM nn US;a [ S5e[R"URU S 9n [R"URU S 9n [R"USSS 9U SS2SS24'[R"USS S 9U SS2SS24'[U S-U S--5n[X5nU[- n[ U5Vs/sHnSU-[-U- [- PM nn[R"U4UR-U S 9n[U5H`un n[!U[R""UU- 5-5UU SS2SS24'[R$"UU SS2SS24U5UU SS2SS24'Mb US /U-n[R"US-4UR-U S 9n[ US-5H7n [ U5H%n['UUSS2SS24X{S S 9UU USS2SS24'M' M9 [ U5Vs/sHnS[-U-U- PM nnX4-S-U-n[R"UURS SU-- URSSU-- 4U S 9nUS SS2X"*2X"*24USU2SS2SS24'Un[ U5Hn [ U5HnU[)[+X[,R."UU5-55-nURSU-nU[)[+X[,R""UU5-55-nURSU-nUU S-SS2UU2UU24UUUU-2SS2SS24'UU- nM M USS2SSU2SSU24nUR1S S5R1SS5nUS:waUS- nUS:Xa1U[R2"USS9SS2SS2[R44-nOUS:Xa=U[[R2"US-SS95SS2SS2[R44-nOyUS:Xas[ S UU5Hbn [[R2"USS2SS2XU-24S-SS95nUSS2SS2XU-24==USS2SS2[R44-ss'Md U (Ga[7U5n[ URS 5GHn [ URS5GHn/SQn X-U-n!UU-U-n"[8R:"U!U"[)US 55un#n$n%[8R<"UU#U$4U U%S9 [R>"UU USS245n&[U5Hun'nUU UU'4U&- n(US U(-[,R."U5-n US U(-[,R""U5-n [8R@"U!U"[)U!U -5[)U"U -55un#n$n%[8R<"UU#U$4U U%S9 M [U5GHun)n*[ SU)-5U- n+SU+- SU+4n [U5GHmun,n-U![)[+U*[,R."U-5-55-n.U"[)[+U*[,R""U-5-55-n/[8R:"U.U/[)UU)S-55un#n$n%[8R<"UU#U$4U U%S9 [U5Hun'nUU UUU)U-U--U,U--U'-4n(U(U&-n(UU)S-U(-[,R."U5-n UU)S-U(-[,R""U5-n [8R@"U.U/[)U.U -5[)U/U -55un#n$n%[8R<"UU#U$4U U%S9 M GMp GM GM GM UU4$U$s sn fs sn fs snfs snf)a Extract DAISY feature descriptors densely for the given image. DAISY is a feature descriptor similar to SIFT formulated in a way that allows for fast dense extraction. Typically, this is practical for bag-of-features image representations. The implementation follows Tola et al. [1]_ but deviate on the following points: * Histogram bin contribution are smoothed with a circular Gaussian window over the tonal range (the angular range). * The sigma values of the spatial Gaussian smoothing in this code do not match the sigma values in the original code by Tola et al. [2]_. In their code, spatial smoothing is applied to both the input image and the center histogram. However, this smoothing is not documented in [1]_ and, therefore, it is omitted. Parameters ---------- image : (M, N) array Input image (grayscale). step : int, optional Distance between descriptor sampling points. radius : int, optional Radius (in pixels) of the outermost ring. rings : int, optional Number of rings. histograms : int, optional Number of histograms sampled per ring. orientations : int, optional Number of orientations (bins) per histogram. normalization : [ 'l1' | 'l2' | 'daisy' | 'off' ], optional How to normalize the descriptors * 'l1': L1-normalization of each descriptor. * 'l2': L2-normalization of each descriptor. * 'daisy': L2-normalization of individual histograms. * 'off': Disable normalization. sigmas : 1D array of float, optional Standard deviation of spatial Gaussian smoothing for the center histogram and for each ring of histograms. The array of sigmas should be sorted from the center and out. I.e. the first sigma value defines the spatial smoothing of the center histogram and the last sigma value defines the spatial smoothing of the outermost ring. Specifying sigmas overrides the following parameter. ``rings = len(sigmas) - 1`` ring_radii : 1D array of int, optional Radius (in pixels) for each ring. Specifying ring_radii overrides the following two parameters. ``rings = len(ring_radii)`` ``radius = ring_radii[-1]`` If both sigmas and ring_radii are given, they must satisfy the following predicate since no radius is needed for the center histogram. ``len(ring_radii) == len(sigmas) + 1`` visualize : bool, optional Generate a visualization of the DAISY descriptors Returns ------- descs : array Grid of DAISY descriptors for the given image as an array dimensionality (P, Q, R) where ``P = ceil((M - radius*2) / step)`` ``Q = ceil((N - radius*2) / step)`` ``R = (rings * histograms + 1) * orientations`` descs_img : (M, N, 3) array (only if visualize==True) Visualization of the DAISY descriptors. References ---------- .. [1] Tola et al. "Daisy: An efficient dense descriptor applied to wide- baseline stereo." Pattern Analysis and Machine Intelligence, IEEE Transactions on 32.5 (2010): 815-830. .. [2] http://cvlab.epfl.ch/software/daisy rimgNz"`len(sigmas)-1 != len(ring_radii)`)l1l2daisyoffzInvalid normalization method.)dtype)naxisrreflect)sigmamoderg|=r)rrr)rrr)alpha)!r r rlen ValueErrorrangefloatnpzerosshapediffrrrempty enumeratercosmultiplyr introundmathsinswapaxessumnewaxisr rcircle_perimeter_aa set_colormaxline_aa)0imagestepradiusrings histograms orientations normalizationsigmas ring_radii visualize float_dtypeidxdygrad_maggrad_oriorientation_kappaoorientation_angleshist hist_smoothjtheta desc_dimsdescsidxy_miny_maxx_minx_maxnorms descs_imgcolordesc_ydesc_xrowscolsvalmax_bino_numbin_sizer_numr color_offsett_numthist_yhist_xs0 ڤC:\Users\johnn\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.13_qbz5n2kfra8p0\LocalCache\local-packages\Python313\site-packages\skimage/feature/_daisy.pyrr sD UAu  E++K   " K!Os: .=>>JB F a ~?DU|L|!AE"U1u9%55|L?DU|L|!A&u5| L88899 %++[ 1B %++[ 1B!!,Bq#2#vJ!!,BssAvJBEBEM"HrH$r)BG BUVBUQ!a%"*|3b8BUV 88\Oekk1 ED,-1-x!|0DDEQ1W  DAqM8<Q1W .Qi[6 !F((EAI<$**4KHK 519 |$A&.Q1W VYY'K1a #%/4J.? @.?QVaZ* $.?E @#a'<7I HH EKKNQZ/Q!f*1LM E"-Q6'>6'>-Q!RE-<-A  C 5\z"ASz}txxa7I'I!JKKEKKNU*ESz}txxa7I'I!JKKEKKNU*E4?Aq%+uU{25E#l**Aq0 1 < C# !VtVVtV# $E NN1a ) )!Q /E  D RVVE*1a+;< *!F*TF*"&":":FCq N#dCy4,SI&&q!Qw0 )*< =HE1$Q5[1G;HX- ;BX- ;B&*llFRK(8#frk:J'OD$NN9tTlEM!>!** 5HE1#(U#3e#;L-q,?E$-e$4q!'#eA O.D*E!E!'#eA O.D*E!E*.*B*B"FCuqy0A,B+dCy4,SQ(12D(EHE1', ! ! ,"'*"4|"C!D"',"6!7#(!(!)(H%/H!' !2X!= !KB!' !2X!= !KB.2ll &FRK0@#frkBR/OD$!NN9tTlEQTU!)F%5!6'+'`i qMLW$ As a;7b bb ) rgrNNF)r*numpyr rrrrr util.dtyper _shared.filtersr _shared.utilsr rSr rrcrosC ((%&$  lrn