IEEE Trans Pattern Anal Mach Intell - CPMC: Automatic Object Segmentation Using Constrained Parametric Min-Cuts.

Tópicos

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

Resumo

We present a novel framework to generate and rank plausible hypotheses for the spatial extent of objects in images using bottom-up computational processes and mid-level selection cues. The object hypotheses are represented as figure-ground segmentations, and are extracted automatically, without prior knowledge of the properties of individual object classes, by solving a sequence of Constrained Parametric Min-Cut problems (CPMC) on a regular image grid. In a subsequent step, we learn to rank the corresponding segments by training a continuous model to predict how likely they are to exhibit real-world regularities (expressed as putative overlap with ground truth) based on their mid-level region properties, then diversify the estimated overlap score using maximum marginal relevance measures. We show that this algorithm significantly outperforms the state of the art for low-level segmentation in the VOC 2009 and 2010 data sets. In our companion papers [1], [2], we show that the algorithm can be used, successfully, in a segmentation-based visual object category recognition pipeline. This architecture ranked first in the VOC2009 and VOC2010 image segmentation and labeling challenges.

Resumo Limpo

present novel framework generat rank plausibl hypothes spatial extent object imag use bottomup comput process midlevel select cue object hypothes repres figureground segment extract automat without prior knowledg properti individu object class solv sequenc constrain parametr mincut problem cpmc regular imag grid subsequ step learn rank correspond segment train continu model predict like exhibit realworld regular express putat overlap ground truth base midlevel region properti diversifi estim overlap score use maximum margin relev measur show algorithm signific outperform state art lowlevel segment voc data set companion paper show algorithm can use success segmentationbas visual object categori recognit pipelin architectur rank first voc voc imag segment label challeng

Resumos Similares

IEEE Trans Image Process - Shape sparse representation for joint object classification and segmentation. ( 0,76336514313393 )
IEEE Trans Image Process - Spatio-temporal video segmentation with shape growth or shrinkage constraint. ( 0,739968504653918 )
Comput. Biol. Med. - Effective fuzzy c-means based kernel function in segmenting medical images. ( 0,721682793320809 )
IEEE Trans Vis Comput Graph - Uncluttered Single-Image Visualization of Vascular Structures Using GPU and Integer Programming. ( 0,719583259026076 )
IEEE Trans Vis Comput Graph - Supervised Manifold Distance Segmentation. ( 0,716428955986438 )
IEEE Trans Image Process - Weighted similarity-invariant linear algorithm for camera calibration with rotating 1D objects. ( 0,708386353472998 )
Methods Inf Med - ML segmentation strategies for object interference compensation in FDG-PET lesion quantification. ( 0,698122685675947 )
IEEE Trans Image Process - Automatic image segmentation by dynamic region merging. ( 0,69658111095963 )
IEEE Trans Image Process - VE-LLI-VO: vessel enhancement using local line integrals and variational optimization. ( 0,69285516598861 )
IEEE Trans Image Process - Automatic segmentation of the left atrium from MR images via variational region growing with a moments-based shape prior. ( 0,686679584964883 )
Int J Comput Assist Radiol Surg - Voxel classification and graph cuts for automated segmentation of pathological periprosthetic hip anatomy. ( 0,682707954171888 )
Int J Comput Assist Radiol Surg - Local/non-local regularized image segmentation using graph-cuts: application to dynamic and multispectral MRI. ( 0,682271986568226 )
IEEE Trans Image Process - Automatic bootstrapping and tracking of object contours. ( 0,677807645083849 )
IEEE Trans Pattern Anal Mach Intell - Paired Regions for Shadow Detection and Removal. ( 0,676159878762368 )
IEEE Trans Image Process - Landmark image super-resolution by retrieving web images. ( 0,674116938765283 )
IEEE Trans Image Process - GPU accelerated edge-region based level set evolution constrained by 2D gray-scale histogram. ( 0,673015995607882 )
Comput Math Methods Med - Retrieval of brain tumors with region-specific bag-of-visual-words representations in contrast-enhanced MRI images. ( 0,672898371733705 )
Comput. Biol. Med. - Segmentation of anterior cruciate ligament in knee MR images using graph cuts with patient-specific shape constraints and label refinement. ( 0,672632163533572 )
IEEE Trans Image Process - Multi-class constrained normalized cut with hard, soft, unary and pairwise priors and its applications to object segmentation. ( 0,66848734797558 )
Int J Comput Assist Radiol Surg - Automatic left ventricle segmentation in volumetric SPECT data set by variational level set. ( 0,668317440809533 )
Comput. Biol. Med. - A hierarchical model for automatic nuchal translucency detection from ultrasound images. ( 0,66773590017917 )
IEEE Trans Image Process - 3D superalloy grain segmentation using a multichannel edge-weighted centroidal Voronoi tessellation algorithm. ( 0,66737865995772 )
Comput. Biol. Med. - A level-set based approach for anterior teeth segmentation in cone beam computed tomography images. ( 0,665772030755832 )
Comput. Biol. Med. - Nearly automated motion artifacts correction between multi breath-hold short-axis and long-axis cine CMR images. ( 0,664606180708454 )
Comput Math Methods Med - A hybrid method for pancreas extraction from CT image based on level set methods. ( 0,662765686228449 )
IEEE Trans Neural Netw Learn Syst - MTC: A Fast and Robust Graph-Based Transductive Learning Method. ( 0,662636681187121 )
IEEE Trans Image Process - The elastic ratio: introducing curvature into ratio-based image segmentation. ( 0,662509616262512 )
Comput Math Methods Med - New region-scalable discriminant and fitting energy functional for driving geometric active contours in medical image segmentation. ( 0,661804120968184 )
IEEE Trans Image Process - On the construction of topology-preserving deformation fields. ( 0,660939854592201 )
Comput Methods Programs Biomed - Obtaining optic disc center and pixel region by automatic thresholding methods on morphologically processed fundus images. ( 0,660413427993732 )
IEEE Trans Pattern Anal Mach Intell - Human Pose Estimation Using Consistent Max Covering. ( 0,660245006916015 )
Comput. Biol. Med. - Reducing redundancy in wireless capsule endoscopy videos. ( 0,66019801818922 )
IEEE Trans Image Process - Self-crossing detection and location for parametric active contours. ( 0,65875496068625 )
Med Biol Eng Comput - Automatic segmentation of brain MR images using an adaptive balloon snake model with fuzzy classification. ( 0,658537744401092 )
Int J Comput Assist Radiol Surg - Extreme leg motion analysis of professional ballet dancers via MRI segmentation of multiple leg postures. ( 0,658530419949901 )
Comput Methods Programs Biomed - Segmentation of pituitary adenoma: a graph-based method vs. a balloon inflation method. ( 0,658486810188252 )
Comput Methods Programs Biomed - Geometrical methods for level set based abdominal aortic aneurysm thrombus and outer wall 2D image segmentation. ( 0,6581994510745 )
Int J Comput Assist Radiol Surg - 3D variational brain tumor segmentation using Dirichlet priors on a clustered feature set. ( 0,656627648718291 )
IEEE J Biomed Health Inform - Accurate segmentation of partially overlapping cervical cells based on dynamic sparse contour searching and GVF snake model. ( 0,655924917171279 )
Comput. Biol. Med. - Phase-based probabilistic active contour for nerve detection in ultrasound images for regional anesthesia. ( 0,655052909256783 )
IEEE Trans Image Process - Incorporating anatomical side information into PET reconstruction using nonlocal regularization. ( 0,653966097337007 )
IEEE Trans Image Process - A filtering approach to edge preserving MAP estimation of images. ( 0,651103061951383 )
IEEE Trans Image Process - A novel rotationally invariant region-based hidden Markov model for efficient 3-D image segmentation. ( 0,650928203194257 )
Int J Comput Assist Radiol Surg - Automatic generation of anatomic characteristics from cerebral aneurysm surface models. ( 0,650305978847042 )
J Med Syst - Brain MR image segmentation with spatial constrained K-mean algorithm and dual-tree complex wavelet transform. ( 0,650132033070568 )
Neural Comput - Continuation-based numerical detection of after-depolarization and spike-adding thresholds. ( 0,648615603703285 )
IEEE Trans Image Process - Overlapping cell nuclei segmentation using a spatially adaptive active physical model. ( 0,648603884042382 )
Int J Comput Assist Radiol Surg - Segmentation of radiographic images under topological constraints: application to the femur. ( 0,644829155173747 )
Comput Math Methods Med - Diabetic retinopathy grading by digital curvelet transform. ( 0,643140452711845 )
J Med Syst - Automated bleeding detection in capsule endoscopy videos using statistical features and region growing. ( 0,642304950765134 )
IEEE Trans Image Process - Variable length open contour tracking using a deformable trellis. ( 0,642096650102616 )
Comput. Biol. Med. - Automatic brain extraction methods for T1 magnetic resonance images using region labeling and morphological operations. ( 0,641506400580898 )
IEEE Trans Pattern Anal Mach Intell - Spatial and Anatomical Regularization of SVM: A General Framework for Neuroimaging Data. ( 0,640971226285603 )
IEEE Trans Image Process - Interpolation-dependent image downsampling. ( 0,640648388961189 )
Comput Methods Programs Biomed - A novel method for pulmonary embolism detection in CTA images. ( 0,640434602276399 )
J Clin Monit Comput - A comparison of two algorithms for automated stone detection in clinical B-mode ultrasound images of the abdomen. ( 0,639073584361859 )
IEEE Trans Image Process - Minimization of monotonically levelable higher order MRF energies via graph cuts. ( 0,638876969188346 )
Int J Comput Assist Radiol Surg - Computer-aided nidus segmentation and angiographic characterization of arteriovenous malformations. ( 0,638662608680634 )
IEEE J Biomed Health Inform - A spatiotemporal-based scheme for efficient registration-based segmentation of thoracic 4-D MRI. ( 0,638654057089124 )
IEEE Trans Image Process - Framelet-based blind motion deblurring from a single image. ( 0,637970821815896 )
IEEE Trans Image Process - Winding number constrained contour detection. ( 0,63744377582651 )
IEEE Trans Image Process - Connectivity-enforcing Hough transform for the robust extraction of line segments. ( 0,636904064729736 )
IEEE J Biomed Health Inform - Segmentation of tumor and edema along with healthy tissues of brain using wavelets and neural networks. ( 0,636668920109516 )
Int J Comput Assist Radiol Surg - Patch-based label fusion segmentation of brainstem structures with dual-contrast MRI for Parkinson's disease. ( 0,634962654329972 )
Med Biol Eng Comput - A review of ultrasound common carotid artery image and video segmentation techniques. ( 0,633480931155401 )
Int J Comput Assist Radiol Surg - Automatic definition of the central-chest lymph-node stations. ( 0,63262695498859 )
Int J Comput Assist Radiol Surg - Delineation of blood vessels in pediatric retinal images using decision trees-based ensemble classification. ( 0,632314339483267 )
IEEE Trans Image Process - Non-Lipschitz lp-regularization and box constrained model for image restoration. ( 0,630698738603784 )
Int J Comput Assist Radiol Surg - Brain tumor detection and segmentation in a CRF (conditional random fields) framework with pixel-pairwise affinity and superpixel-level features. ( 0,630427955113265 )
IEEE Trans Image Process - Active contour-based visual tracking by integrating colors, shapes, and motions. ( 0,63030593830773 )
Comput. Biol. Med. - A robust medical image segmentation method using KL distance and local neighborhood information. ( 0,629614897770821 )
Comput Math Methods Med - Sparse reconstruction for bioluminescence tomography based on the semigreedy method. ( 0,629391292192609 )
Comput. Biol. Med. - Fast segmentation of bone in CT images using 3D adaptive thresholding. ( 0,628962433786966 )
Int J Comput Assist Radiol Surg - Spatially adaptive active contours: a semi-automatic tumor segmentation framework. ( 0,628422863246021 )
Comput. Biol. Med. - 3D geometric split-merge segmentation of brain MRI datasets. ( 0,627692849844897 )
Comput Methods Programs Biomed - Simple methods for segmentation and measurement of diabetic retinopathy lesions in retinal fundus images. ( 0,627498943823808 )
Int J Comput Assist Radiol Surg - Automated liver lesion detection in CT images based on multi-level geometric features. ( 0,627152508699586 )
Comput. Biol. Med. - Fully automated liver segmentation from SPIR image series. ( 0,626952535311672 )
Comput Methods Programs Biomed - pSnakes: a new radial active contour model and its application in the segmentation of the left ventricle from echocardiographic images. ( 0,626319193786034 )
Comput Math Methods Med - Segmentation of brain MRI using SOM-FCM-based method and 3D statistical descriptors. ( 0,626060636491715 )
Comput. Biol. Med. - Automated retinal layers segmentation in SD-OCT images using dual-gradient and spatial correlation smoothness constraint. ( 0,624949848992171 )
IEEE Trans Image Process - Image segmentation using fuzzy region competition and spatial/frequency information. ( 0,624712683098152 )
IEEE Trans Image Process - Variational region-based segmentation using multiple texture statistics. ( 0,623690874343213 )
Comput Math Methods Med - A hybrid approach of using symmetry technique for brain tumor segmentation. ( 0,622630917622448 )
Med Biol Eng Comput - Automatic segmentation of carotid B-mode images using fuzzy classification. ( 0,621043432367057 )
Comput. Biol. Med. - Estimating contrast agent motion from ultrasound images using an anisotropic diffusion-based optical flow technique. ( 0,62006712453294 )
Comput. Biol. Med. - Refinement of lung nodule candidates based on local geometric shape analysis and Laplacian of Gaussian kernels. ( 0,61993971251349 )
Int J Comput Assist Radiol Surg - Automatic 3D segmentation of individual facial muscles using unlabeled prior information. ( 0,616995471955487 )
IEEE Trans Image Process - Multivariate image segmentation using semantic region growing with adaptive edge penalty. ( 0,616875481934159 )
IEEE Trans Pattern Anal Mach Intell - Multi-Atlas Segmentation with Joint Label Fusion. ( 0,61621818704597 )
Comput. Biol. Med. - Retinal vessel segmentation using a multi-scale medialness function. ( 0,616096394953389 )
Comput. Biol. Med. - Gallbladder shape extraction from ultrasound images using active contour models. ( 0,615911830645103 )
IEEE Trans Image Process - Adjoint active surfaces for localization and imaging. ( 0,61580312044197 )
Int J Comput Assist Radiol Surg - Vertebra identification using template matching modelmp and K-means clustering. ( 0,61525382751665 )
IEEE Trans Image Process - An automatic graph-based approach for artery/vein classification in retinal images. ( 0,613344237327811 )
Med Biol Eng Comput - Automatic segmentation of the fetal cerebellum on ultrasound volumes, using a 3D statistical shape model. ( 0,61294661669178 )
Comput Methods Programs Biomed - Automatic selection of arterial input function on dynamic contrast-enhanced MR images. ( 0,61259926044857 )
Comput. Biol. Med. - Prioritization of brain MRI volumes using medical image perception model and tumor region segmentation. ( 0,611741389878017 )
Comput Math Methods Med - Multiple active contours driven by particle swarm optimization for cardiac medical image segmentation. ( 0,611175702968953 )
J Digit Imaging - Dual-pass feature extraction on human vessel images. ( 0,610873519167705 )