IEEE Trans Image Process - Lookup-table-based gradient field reconstruction.

Tópicos

{ imag(2830) propos(1344) filter(1198) }
{ method(984) reconstruct(947) comput(926) }
{ structur(1116) can(940) graph(676) }
{ can(774) often(719) complex(702) }
{ featur(1941) imag(1645) propos(1176) }
{ howev(809) still(633) remain(590) }
{ result(1111) use(1088) new(759) }
{ problem(2511) optim(1539) algorithm(950) }
{ imag(1947) propos(1133) code(1026) }
{ bind(1733) structur(1185) ligand(1036) }
{ learn(2355) train(1041) set(1003) }
{ first(2504) two(1366) second(1323) }
{ can(981) present(881) function(850) }
{ process(1125) use(805) approach(778) }
{ network(2748) neural(1063) input(814) }
{ take(945) account(800) differ(722) }
{ motion(1329) object(1292) video(1091) }
{ control(1307) perform(991) simul(935) }
{ import(1318) role(1303) understand(862) }
{ spatial(1525) area(1432) region(1030) }
{ model(2656) set(1616) predict(1553) }
{ method(1219) similar(1157) match(930) }
{ treatment(1704) effect(941) patient(846) }
{ framework(1458) process(801) describ(734) }
{ chang(1828) time(1643) increas(1301) }
{ algorithm(1844) comput(1787) effici(935) }
{ case(1353) use(1143) diagnosi(1136) }
{ studi(1410) differ(1259) use(1210) }
{ visual(1396) interact(850) tool(830) }
{ perform(1367) use(1326) method(1137) }
{ data(2317) use(1299) case(1017) }
{ cost(1906) reduc(1198) effect(832) }
{ activ(1138) subject(705) human(624) }
{ activ(1452) weight(1219) physic(1104) }
{ method(1969) cluster(1462) data(1082) }
{ method(2212) result(1239) propos(1039) }
{ model(3404) distribut(989) bayesian(671) }
{ data(1737) use(1416) pattern(1282) }
{ inform(2794) health(2639) internet(1427) }
{ system(1976) rule(880) can(841) }
{ measur(2081) correl(1212) valu(896) }
{ imag(1057) registr(996) error(939) }
{ sequenc(1873) structur(1644) protein(1328) }
{ featur(3375) classif(2383) classifi(1994) }
{ imag(2675) segment(2577) method(1081) }
{ patient(2315) diseas(1263) diabet(1191) }
{ studi(2440) review(1878) systemat(933) }
{ assess(1506) score(1403) qualiti(1306) }
{ surgeri(1148) surgic(1085) robot(1054) }
{ error(1145) method(1030) estim(1020) }
{ concept(1167) ontolog(924) domain(897) }
{ clinic(1479) use(1117) guidelin(835) }
{ extract(1171) text(1153) clinic(932) }
{ method(1557) propos(1049) approach(1037) }
{ data(1714) softwar(1251) tool(1186) }
{ design(1359) user(1324) use(1319) }
{ model(2220) cell(1177) simul(1124) }
{ care(1570) inform(1187) nurs(1089) }
{ general(901) number(790) one(736) }
{ search(2224) databas(1162) retriev(909) }
{ data(3963) clinic(1234) research(1004) }
{ risk(3053) factor(974) diseas(938) }
{ perform(999) metric(946) measur(919) }
{ research(1085) discuss(1038) issu(1018) }
{ system(1050) medic(1026) inform(1018) }
{ model(2341) predict(2261) use(1141) }
{ compound(1573) activ(1297) structur(1058) }
{ studi(1119) effect(1106) posit(819) }
{ blood(1257) pressur(1144) flow(957) }
{ record(1888) medic(1808) patient(1693) }
{ health(3367) inform(1360) care(1135) }
{ model(3480) simul(1196) paramet(876) }
{ monitor(1329) mobil(1314) devic(1160) }
{ ehr(2073) health(1662) electron(1139) }
{ state(1844) use(1261) util(961) }
{ research(1218) medic(880) student(794) }
{ patient(2837) hospit(1953) medic(668) }
{ age(1611) year(1155) adult(843) }
{ medic(1828) order(1363) alert(1069) }
{ signal(2180) analysi(812) frequenc(800) }
{ group(2977) signific(1463) compar(1072) }
{ sampl(1606) size(1419) use(1276) }
{ gene(2352) biolog(1181) express(1162) }
{ data(3008) multipl(1320) sourc(1022) }
{ intervent(3218) particip(2042) group(1664) }
{ time(1939) patient(1703) rate(768) }
{ patient(1821) servic(1111) care(1106) }
{ use(2086) technolog(871) perceiv(783) }
{ analysi(2126) use(1163) compon(1037) }
{ health(1844) social(1437) communiti(874) }
{ high(1669) rate(1365) level(1280) }
{ cancer(2502) breast(956) screen(824) }
{ use(976) code(926) identifi(902) }
{ use(1733) differ(960) four(931) }
{ drug(1928) target(777) effect(648) }
{ implement(1333) system(1263) develop(1122) }
{ survey(1388) particip(1329) question(1065) }
{ estim(2440) model(1874) function(577) }
{ decis(3086) make(1611) patient(1517) }
{ detect(2391) sensit(1101) algorithm(908) }

Resumo

In computer vision, there are many applications, where it is advantageous to process an image in the gradient domain and then reintegrate the gradient field: important examples include shadow removal, lightness calculation, and data fusion. A serious problem with this approach is that the reconstruction step often introduces artefacts-commonly, smoothed and smeared edges-to the recovered image. This is a result of the inherent ill-posedness of reintegrating a nonintegrable field. Artefacts can be diminished but not removed, by using complex to highly complex reintegration techniques. Here, we present a remarkably simple (and on the face of it naive) algorithm for reconstructing gradient fields. Suppose we start with a multichannel original, and from it derive a (possibly one of many) 1-D gradient field; for many applications, the derived gradient field will be nonintegrable. Here, we propose a lookup-table-based map relating the multichannel original to a reconstructed scalar output image, whose gradient best matches the target gradient field. The idea, at base, is that if we learn how to map the gradients of the multichannel original onto the desired output gradient, and then using the lookup table (LUT) constraint, we effectively derive the mapping from the multichannel input to the desired, reintegrated, image output. While this map could take a variety of forms, here we derive the best map from the multichannel gradient as a (nonlinear) function of the input to each of the target scalar gradients. In this framework, reconstruction is a simple equation-solving exercise of low dimensionality. One obvious application of our method is to the image-fusion problem, e.g., the problem of converting a color or higher-D image into grayscale. We will show, through extensive experiments and complementary theoretical arguments, that our straightforward method preserves the target contrast as well as do complex previous reintegration methods, but without artefacts, and with a substantially cheaper computational cost. Finally, we demonstrate the generality of the method by applying it to gradient field reconstruction in an additional area, the shading recovery problem.

Resumo Limpo

comput vision mani applic advantag process imag gradient domain reintegr gradient field import exampl includ shadow remov light calcul data fusion serious problem approach reconstruct step often introduc artefactscommon smooth smear edgesto recov imag result inher illposed reintegr nonintegr field artefact can diminish remov use complex high complex reintegr techniqu present remark simpl face naiv algorithm reconstruct gradient field suppos start multichannel origin deriv possibl one mani d gradient field mani applic deriv gradient field will nonintegr propos lookuptablebas map relat multichannel origin reconstruct scalar output imag whose gradient best match target gradient field idea base learn map gradient multichannel origin onto desir output gradient use lookup tabl lut constraint effect deriv map multichannel input desir reintegr imag output map take varieti form deriv best map multichannel gradient nonlinear function input target scalar gradient framework reconstruct simpl equationsolv exercis low dimension one obvious applic method imagefus problem eg problem convert color higherd imag grayscal will show extens experi complementari theoret argument straightforward method preserv target contrast well complex previous reintegr method without artefact substanti cheaper comput cost final demonstr general method appli gradient field reconstruct addit area shade recoveri problem

Resumos Similares

Int J Comput Assist Radiol Surg - Successive iterative restoration applied to streak artifact reduction in X-ray CT image of dento-alveolar region. ( 0,864498797953894 )
IEEE Trans Image Process - Linear feature separation from topographic maps using energy density and the shear transform. ( 0,862063390374098 )
Comput Math Methods Med - The X-ray transform projection of 3D mother wavelet function. ( 0,842312756198974 )
IEEE Trans Image Process - Stereo matching using epipolar distance transform. ( 0,835894329129761 )
IEEE Trans Image Process - Scanned image descreening with image redundancy and adaptive filtering. ( 0,831070701780047 )
Comput. Biol. Med. - Generalized Gibbs priors based positron emission tomography reconstruction. ( 0,824910011875949 )
IEEE Trans Image Process - Face super-resolution via multilayer locality-constrained iterative neighbor embedding and intermediate dictionary learning. ( 0,81938696632901 )
IEEE Trans Image Process - Interpolation-based image super-resolution using multisurface fitting. ( 0,798851543808546 )
J Med Syst - Analysis of enlarged images using time-of-flight magnetic resonance angiography, computed tomography, and conventional angiography. ( 0,79821760747289 )
IEEE Trans Image Process - 3D steerable wavelets in practice. ( 0,797587332962057 )
IEEE Trans Image Process - Higher degree total variation (HDTV) regularization for image recovery. ( 0,795201476138125 )
IEEE Trans Image Process - Adaptive reconstruction of millimeter-wave radiometric images. ( 0,794522311446636 )
IEEE Trans Image Process - IMAGE resolution enhancement by using discrete and stationary wavelet decomposition. ( 0,790490913745675 )
IEEE Trans Image Process - Fast O1 bilateral filtering using trigonometric range kernels. ( 0,784117696451873 )
IEEE Trans Image Process - Multiscale bi-Gaussian filter for adjacent curvilinear structures detection with application to vasculature images. ( 0,784101278416771 )
IEEE Trans Image Process - Naturalness preserved enhancement algorithm for non-uniform illumination images. ( 0,783545058799128 )
IEEE Trans Image Process - Nonlinear image upsampling method based on radial basis function interpolation. ( 0,782052659282856 )
IEEE Trans Image Process - Sparsity-based Poisson denoising with dictionary learning. ( 0,778846856727033 )
IEEE Comput Graph Appl - Multispectral photometric stereo for acquiring high-fidelity surface normals. ( 0,778049309758027 )
IEEE Trans Image Process - Non-linear direct multi-scale image enhancement based on the luminance and contrast masking characteristics of the human visual system. ( 0,777268825615984 )
IEEE Trans Image Process - Reducing integrability error of color tensor gradients for image fusion. ( 0,774253680655389 )
IEEE Trans Image Process - Mixed noise removal by weighted encoding with sparse nonlocal regularization. ( 0,772168282125694 )
IEEE Trans Image Process - Gradient histogram estimation and preservation for texture enhanced image denoising. ( 0,771191290722093 )
IEEE Trans Image Process - Contrast-guided image interpolation. ( 0,770206109154825 )
IEEE Trans Image Process - Content-aware dark image enhancement through channel division. ( 0,768261827951667 )
IEEE Trans Image Process - Nonedge-specific adaptive scheme for highly robust blind motion deblurring of natural imagess. ( 0,767854571510327 )
Comput. Biol. Med. - GPU-accelerated 3D mipmap for real-time visualization of ultrasound volume data. ( 0,7656311967266 )
IEEE Trans Image Process - Cognition and removal of impulse noise with uncertainty. ( 0,764739958079148 )
IEEE Trans Image Process - Edge strength filter based color filter array interpolation. ( 0,764341380543484 )
IEEE Trans Image Process - Luma-chroma space filter design for subpixel-based monochrome image downsampling. ( 0,762954401417692 )
Comput Math Methods Med - Ultrasound image enhancement using structure-based filtering. ( 0,759707986610758 )
IEEE Trans Image Process - Correction of axial and lateral chromatic aberration with false color filtering. ( 0,759273515020295 )
IEEE Trans Image Process - Symmetric smoothing filters from global consistency constraints. ( 0,75903371604907 )
IEEE Trans Image Process - Contextual and variational contrast enhancement. ( 0,756116148038645 )
IEEE Trans Image Process - Optimal inversion of the generalized Anscombe transformation for Poisson-Gaussian noise. ( 0,755740251719866 )
IEEE Trans Image Process - Selectively detail-enhanced fusion of differently exposed images with moving objects. ( 0,755614590251552 )
IEEE Trans Image Process - Multiscale image fusion using the undecimated wavelet transform with spectral factorization and nonorthogonal filter banks. ( 0,754881568882581 )
Int J Med Robot - Dynamic cylindrical free-form deformation for interactive simulation of tool-tissue interaction. ( 0,751965590070164 )
IEEE Trans Image Process - Demosaicking of noisy Bayer-sampled color images with least-squares luma-chroma demultiplexing and noise level estimation. ( 0,75146829252549 )
IEEE Trans Image Process - Weighted guided image filtering. ( 0,75058093015503 )
IEEE Trans Image Process - Sparse representation based image interpolation with nonlocal autoregressive modeling. ( 0,749067530311453 )
IEEE Trans Image Process - An edge-adapting Laplacian kernel for nonlinear diffusion filters. ( 0,748707863242351 )
IEEE Trans Image Process - Automatic single-image-based rain streaks removal via image decomposition. ( 0,747945834527254 )
IEEE Trans Image Process - Efficient contrast enhancement using adaptive gamma correction with weighting distribution. ( 0,746686317407885 )
Comput Math Methods Med - Automatic vasculature identification in coronary angiograms by adaptive geometrical tracking. ( 0,745834407840268 )
Int J Comput Assist Radiol Surg - Wavelet denoising for quantum noise removal in chest digital tomosynthesis. ( 0,744083471068371 )
IEEE Trans Image Process - Adaptive 2-D wavelet transform based on the lifting scheme with preserved vanishing moments. ( 0,739705283159274 )
Comput Methods Programs Biomed - Supervised restoration of degraded medical images using multiple-point geostatistics. ( 0,739125286177722 )
IEEE Trans Image Process - Switching bilateral filter with a texture/noise detector for universal noise removal. ( 0,738342923516149 )
IEEE Trans Image Process - Green noise digital halftoning with multiscale error diffusion. ( 0,737381062480341 )
IEEE Trans Image Process - Multiscale gradients-based color filter array interpolation. ( 0,736069100800327 )
IEEE Trans Image Process - Configuration-Transition-Based Connected-Component Labeling. ( 0,736047929516424 )
IEEE Trans Image Process - Multiclass maximum-likelihood symmetry determination and motif reconstruction of 3-D helical objects from projection images for electron microscopy. ( 0,735172531424355 )
IEEE Trans Image Process - Probabilistic exposure fusion. ( 0,733213064531642 )
IEEE Trans Vis Comput Graph - Admissible Diffusion Wavelets and Their Applications in Space-Frequency Processing. ( 0,731141994200569 )
IEEE Trans Image Process - Contourlet domain multiband deblurring based on color correlation for fluid lens cameras. ( 0,730860243913786 )
IEEE Trans Image Process - Nonlocal hierarchical dictionary learning using wavelets for image denoising. ( 0,729963618003946 )
IEEE Trans Image Process - Commutability of blur and affine warping in super-resolution with application to joint estimation of triple-coupled variables. ( 0,729822804048078 )
IEEE Trans Image Process - Super resolution image reconstruction through Bregman iteration using morphologic regularization. ( 0,727786250810417 )
IEEE Trans Image Process - Unified blind method for multi-image super-resolution and single/multi-image blur deconvolution. ( 0,7276647769842 )
IEEE Trans Vis Comput Graph - A Curvature-Adaptive Implicit Surface Reconstruction for Irregularly Spaced Points. ( 0,727456642165156 )
IEEE Trans Image Process - Nonlinear approach for enhancement of image focus volume in shape from focus. ( 0,726837554919068 )
Comput Math Methods Med - Feature and contrast enhancement of mammographic image based on multiscale analysis and morphology. ( 0,726101099298587 )
IEEE Trans Image Process - A new scheme for robust gradient vector estimation in color images. ( 0,72408716337353 )
IEEE J Biomed Health Inform - An Adaptive Filter for the Removal of Drifting Sinusoidal Noise without a Reference. ( 0,72208395938139 )
IEEE Trans Image Process - Compressibility-aware media retargeting with structure preserving. ( 0,721920770880468 )
Comput. Biol. Med. - Expectation maximization (EM) algorithms using polar symmetries for computed tomography (CT) image reconstruction. ( 0,721752347901499 )
IEEE Trans Image Process - An improved image compression algorithm using binary space partition scheme and geometric wavelets. ( 0,721543904458405 )
IEEE Trans Image Process - Improving shape retrieval by spectral matching and meta similarity. ( 0,719457240573603 )
IEEE Trans Image Process - How to SAIF-ly boost denoising performance. ( 0,717268154824953 )
IEEE Trans Image Process - Contrast-enhanced fusion of multi-sensor images using subband-decomposed multiscale retinex. ( 0,715698709614316 )
IEEE Trans Image Process - Spline regression hashing for fast image search. ( 0,715360185496704 )
IEEE Trans Image Process - Detection and inpainting of facial wrinkles using texture orientation fields and Markov random field modeling. ( 0,714611262314018 )
IEEE Trans Image Process - A new color filter array with optimal properties for noiseless and noisy color image acquisition. ( 0,714373701569595 )
Med Biol Eng Comput - Exploiting sparsity and low-rank structure for the recovery of multi-slice breast MRIs with reduced sampling error. ( 0,713073962421264 )
IEEE Trans Image Process - Segmented gray-code kernels for fast pattern matching. ( 0,712534719200773 )
Comput Math Methods Med - Study on construction of a medical x-ray direct digital radiography system and hybrid preprocessing methods. ( 0,712264724986142 )
Comput Methods Programs Biomed - Automatic detection of the carotid lumen axis in B-mode ultrasound images. ( 0,711195845928688 )
Comput Math Methods Med - Level set segmentation of medical images based on local region statistics and maximum a posteriori probability. ( 0,710538005136076 )
Comput. Biol. Med. - A new method for gridding DNA microarrays. ( 0,710214386979726 )
IEEE Trans Image Process - Optimizing the error diffusion filter for blue noise halftoning with multiscale error diffusion. ( 0,709475654760603 )
Comput Math Methods Med - Improving spatial adaptivity of nonlocal means in low-dosed CT imaging using pointwise fractal dimension. ( 0,707044103543625 )
IEEE Trans Image Process - PDE-based random-valued impulse noise removal based on new class of controlling functions. ( 0,707003539788918 )
Comput Math Methods Med - Improved DCT-based nonlocal means filter for MR images denoising. ( 0,706814927937329 )
IEEE Trans Image Process - Saliency detection in the compressed domain for adaptive image retargeting. ( 0,706658883623226 )
IEEE Trans Image Process - Image Sensor Noise Parameter Estimation by Variance Stabilization and Normality Assessment. ( 0,705767507170861 )
IEEE Trans Image Process - Noise reduction based on partial-reference, dual-tree complex wavelet transform shrinkage. ( 0,705555442263052 )
IEEE Trans Neural Netw Learn Syst - Targeting accurate object extraction from an image: a comprehensive study of natural image matting. ( 0,705392745380223 )
IEEE Trans Image Process - Image processing using smooth ordering of its patches. ( 0,705136788045824 )
IEEE Trans Image Process - Three-dimensional near-field MIMO array imaging using range migration techniques. ( 0,704853073835749 )
Comput. Biol. Med. - A robust algorithm for removing artifacts in EEG recorded during FMRI/EEG study. ( 0,70482166038422 )
IEEE Trans Image Process - Robust image hashing based on random Gabor filtering and dithered lattice vector quantization. ( 0,704109245971605 )
IEEE Trans Image Process - Adaptive quantization-parameter clip scheme for smooth quality in H.264/AVC. ( 0,703196128515113 )
IEEE Trans Image Process - Selection of optimal spectral sensitivity functions for color filter arrays. ( 0,702777636038023 )
IEEE Trans Image Process - Regularized background adaptation: a novel learning rate control scheme for gaussian mixture modeling. ( 0,701242055746359 )
IEEE Trans Image Process - Efficient volume reconstruction for parallel-beam computed laminography by filtered backprojection on multi-core clusters. ( 0,701153860914469 )
Int J Comput Assist Radiol Surg - An algorithm for noise correction of dual-energy computed tomography material density images. ( 0,701085302608976 )
IEEE Trans Image Process - Anisotropic diffusion filter with memory based on speckle statistics for ultrasound images. ( 0,700788319830684 )
IEEE Trans Vis Comput Graph - Linear Correlations between Spatial and Normal Noise in Triangle Meshes. ( 0,70012204745427 )
IEEE Trans Image Process - Iterative truncated arithmetic mean filter and its properties. ( 0,696614012790025 )