2,284 Hits in 3.4 sec

Identifying semi-Invariant Features on Mouse Contours

P.A. Crook, T.C. Lukins, J. Heward, J.D. Armstrong
2008 Procedings of the British Machine Vision Conference 2008  
This paper addresses the problem of reliably fitting an orientated model to video data of laboratory mice assays by specifically locating semi-invariant points on an extracted outline.  ...  Using this contour, we compare three different approaches at locating head, tail-tip and tail-base features that allow us to constrain orientation.  ...  We consider three different approaches to finding suitably invariant -and consequently reliable -features on mouse contour data.  ... 
doi:10.5244/c.22.84 dblp:conf/bmvc/CrookLHA08 fatcat:r2el6v5sajcnfh7p3y32qwxtou

Identifying semi-Invariant Features on Mouse Contours

N.P. Tiilikainen, A.E. Bartoli, S. Olsen
2008 Procedings of the British Machine Vision Conference 2008  
We report convincing registration and retexturing results on cartoon videos.  ...  However, in cases such as cartoon videos, there is a high number of smooth contours and only little or spurious texture.  ...  Based on these criteria the reference frame is chosen using a semi automatic heuristic that presents a selection of candidate frames and lets the user make the final decision.  ... 
doi:10.5244/c.22.91 dblp:conf/bmvc/TiilikainenBO08 fatcat:jo3nc7wu4ndgla3xtru2f2yzry

Tumour Ellipsification in Ultrasound Images for Treatment Prediction in Breast Cancer [article]

Mehrdad J. Gangeh, Hamid R. Tizhoosh, Kan Wu, Dun Huang, Hadi Tadayyon, Gregory J. Czarnota
2017 arXiv   pre-print
One of the earliest steps in using QUS methods is contouring a region of interest (ROI) inside the tumour in ultrasound B-mode images.  ...  The results demonstrated that the proposed method can potentially be used as the first stage in a computer-assisted cancer response prediction system for semi-automated contouring of breast tumours.  ...  Most of these methods, when applied to digital images, rely on the availability of invariant features.  ... 
arXiv:1701.03779v1 fatcat:f5lq62puknc4dbp5aq4t6kqnyq

Algorithm for Automatic Behavior Quantification of Laboratory Mice Using High-Frame-Rate Videos

Yuman NIE, Takeshi TAKAKI, Idaku ISHII, Hiroshi MATSUDA
2011 SICE Journal of Control Measurement and System Integration  
Even when a mouse changes its posture and orientation relative to the camera, these features can still be extracted from the shift-and orientation-invariant shape of the mouse silhouette by using the polar  ...  Multiple repetitive motions can always be identified from periodic frame-differential image features in four segmented regions-the head, left side, right side, and tail.  ...  [10] identified semi-invariant features in mouse contours for robust behavior recognition. Fröhlich et al. [11] applied advanced machine learning methods to analyze rat behavior.  ... 
doi:10.9746/jcmsi.4.322 fatcat:kduf2odhvffk7evtireq2vn54a

Shape Matching Based on Multi-scale Invariant Features

Zhang Kun, Ma Xiao, Li Xinguo
2019 IEEE Access  
of contour sequence, and shape geometry feature.  ...  INDEX TERMS Shape matching, improved discrete curve evolution, multi-scale invariant features, cyclic Smith-Waterman algorithm.  ...  of the mouse.  ... 
doi:10.1109/access.2019.2935879 fatcat:tpfrpvpyovcmxone5ngbjzxnn4

Geometry Processing of Conventionally Produced Mouse Brain Slice Images [article]

Nitin Agarwal, Xiangmin Xu, Gopi Meenakshisundaram
2017 arXiv   pre-print
These image pairs are aligned using a geometric approach through contour images.  ...  This is achieved first by constructing a virtual 3D mouse brain model from annotated slices of Allen Reference Atlas (ARA).  ...  ACKNOWLEDGMENTS The authors would like to thank Dr Hong-Wei Dong for providing the mouse brain atlas images.  ... 
arXiv:1712.09684v1 fatcat:md6zahkcbzfqzduz7djn5er2di

Semi-automatic segmentation of subcutaneous tumours from micro-computed tomography images

Rehan Ali, Cigdem Gunduz-Demir, Tünde Szilágyi, Ben Durkee, Edward E Graves
2013 Physics in Medicine and Biology  
Local phase feature detection is used to highlight the faint boundary features, and a level set-based active contour is used to generate smooth contours that fit the sparse boundary features.  ...  These are used as the basis of our semi-automatic segmentation algorithm.  ...  By using an intensity-invariant feature detection method to emphasize these features, along with an active contour with a strong smoothness constraint, it is possible to develop an algorithm that can automatically  ... 
doi:10.1088/0031-9155/58/22/8007 pmid:24168809 pmcid:PMC4077626 fatcat:huabrizucbbw5mp6mimqb55gkq

InShaDe: Invariant Shape Descriptors for Visual Analysis of Histology 2D Cellular and Nuclear Shapes

Marco Agus, Khaled Al-Thelaya, Corrado Cali, Marina M. Boido, Yin Yang, Giovanni Pintore, Enrico Gobbetti, Jens Schneider
2020 Eurographics Workshop on Visual Computing for Biomedicine  
The optional scale-invariance is achieved by scaling features to z-scores, while invariance under parameterization shifts is achieved by using elliptic Fourier analysis (EFA) on the resulting curvature  ...  The framework is based on a novel shape descriptor of closed contours relying on a geodesically uniform resampling of discrete curves to allow for discrete differential-geometry-based computation of unsigned  ...  In addition, the optional feature scaling step (3.5) ensures invariance under uniform scaling.  ... 
doi:10.2312/vcbm.20201173 dblp:conf/vcbm/AgusACBYPGS20 fatcat:l2s7zbn7rrh2fjrcxfbo4iq5qq

Iterate Cluster: Iterative Semi-Supervised Action Recognition [article]

Jingyuan Li, Eli Shlizerman
2020 arXiv   pre-print
We propose a novel system for active semi-supervised feature-based action recognition. Given time sequences of features tracked during movements our system clusters the sequences into actions.  ...  We test the approach on human skeleton-based action recognition benchmarks assuming that only annotations chosen by our method are available and on mouse movements videos recorded in lab experiments.  ...  PC on UWA3D dataset and and also on Mouse dataset in Table 2 .  ... 
arXiv:2006.06911v1 fatcat:qnxmqge6sfcqlnhxacdomqqjwu

Live-wire 3D medical images segmentation [article]

Ognjen Arandjelovic
2013 arXiv   pre-print
This report also proposes two improvements to the original method, path heating and a new graph edge feature function based on variance of path properties along the boundary.  ...  User's time and involvement is further reduced by allowing him to specify object contours in planes orthogonal to the slices.  ...  The goal is to identify features of the edge pixels and use them in estimating the probability of a pixel belonging to an edge.  ... 
arXiv:1306.3415v1 fatcat:s6fedztfy5cxtgcmfrpkonbjge

A Hybrid Detection and Classification System for Human Motion Analysis [chapter]

Ken Tabb, Neil Davey, Rod Adams, Stella George
2002 Hybrid Information Systems  
The axis crossover vector method is used for translating the active contour into a scale-. location-, resolution-and rotation-invariant vector suited for input to a neural network, and we identify the  ...  Users would initialise a contour loosely around the target object in an image by using a mouse to place the contour s control points in the image.  ...  Potential uses for this application would be the medical domain or semi-automatic CCTV systems, providing an indication to a human observer that a certain event has occurred.  ... 
doi:10.1007/978-3-7908-1782-9_11 fatcat:zv6k76powvbgrer5juvwwjdpne

Terabyte-scale supervised 3D training and benchmarking dataset of the mouse kidney [article]

Willy Kuo, Diego Rossinelli, Georg Schulz, Roland H. Wenger, Simone Hieber, Bert Müller, Vartan Kurtcuoglu
2021 arXiv   pre-print
The HR-Kidney dataset presented in this work bridges this gap by providing 1.7 TB of artefact-corrected synchrotron radiation-based X-ray phase-contrast microtomography images of whole mouse kidneys and  ...  These features were further convolved with a low pass filter kernel to enforce the emergence of local invariances. The generated feature maps were fed to a dense, feed-forward neural network.  ...  Other datasets for machine learning-based segmentation of high-resolution vascular data on the whole mouse organ scale, such as TubeMap 16 and VesSAP 17 , are based on 3D light sheet microscopy images  ... 
arXiv:2108.02226v1 fatcat:zaavornzurg4jipf7jppn6jxhi

DeepSqueak: a deep learning-based system for detection and analysis of ultrasonic vocalizations

Kevin R. Coffey, Russell G. Marx, John F. Neumaier
2019 Neuropsychopharmacology  
analysis, DeepSqueak was able to reduce false positives, increase detection recall, dramatically reduce analysis time, optimize automatic syllable classification, and perform automatic syntax analysis on  ...  DeepSqueak was engineered to allow non-experts easy entry into USV detection and analysis yet is flexible and adaptable with a graphical user interface and offers access to numerous input and analysis features  ...  In MUPET, clustering is applied on the spectral magnitude of the segmented syllables, whereas clustering in DeepSqueak is amplitude invariant and contour-based.  ... 
doi:10.1038/s41386-018-0303-6 pmid:30610191 pmcid:PMC6461910 fatcat:f5uxh2qsn5h7vhxc6mnajhrwbu

HARLEY: A Semi-Automated detection of foci in fluorescence images of yeast [article]

Ilya Shabanov, J. Ross Buchan
2021 bioRxiv   pre-print
After a brief model training on ~20 cells the detection of foci is fully automated and based on closed loops in intensity contours, constrained only by the a-priori known size of the features of interest  ...  Candidate features are annotated with a set of geometrical and intensity-based properties to train a kernel Support Vector Machine to recognize features of interest.  ...  Detected maxima thus not only contain spatial coordinates of the feature, but also a scale corresponding to the size of the feature making them scale invariant.  ... 
doi:10.1101/2021.11.29.470484 fatcat:aq7obhn5znanzjgijrjexrdbbm

Regional Localization of Mouse Brain Slices Based on Unified Modal Transformation

Songwei Wang, Yuhang Wang, Ke Niu, Qian Li, Xiaoping Rao, Hui Zhao, Liwei Chen, Li Shi
2021 Symmetry  
) network, which is based on a symmetric encoder–decoder.  ...  The premise of related analysis is to determine the brain region of each site on the brain slice by referring to the Allen Reference Atlas (ARA), namely the regional localization of the brain slice.  ...  (2) Using Photoshop and ImageJ image processing software, the contours of the ARA are extracted and corrected to realize a simple semi-automatic region division of brain slice images.  ... 
doi:10.3390/sym13060929 fatcat:f2onhdskpzdxlfere3okxhokdm
« Previous Showing results 1 — 15 out of 2,284 results