Title | ||
---|---|---|
Multiple hypotheses image segmentation and classification with application to dietary assessment. |
Abstract | ||
---|---|---|
We propose a method for dietary assessment to automatically identify and locate food in a variety of images captured during controlled and natural eating events. Two concepts are combined to achieve this: a set of segmented objects can be partitioned into perceptually similar object classes based on global and local features; and perceptually similar object classes can be used to assess the accuracy of image segmentation. These ideas are implemented by generating multiple segmentations of an image to select stable segmentations based on the classifier's confidence score assigned to each segmented image region. Automatic segmented regions are classified using a multichannel feature classification system. For each segmented region, multiple feature spaces are formed. Feature vectors in each of the feature spaces are individually classified. The final decision is obtained by combining class decisions from individual feature spaces using decision rules. We show improved accuracy of segmenting food images with classifier feedback. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1109/JBHI.2014.2304925 | IEEE J. Biomedical and Health Informatics |
Keywords | Field | DocType |
automatic food location,image capture,multiple hypothesis image segmentation,segmented region classification,image matching,dietary assessment,biomedical optical imaging,decision making,classifier confidence score assignment,perceptually similar object class,decision rule,image segmentation,dietary assessment application,food image segmention accuracy,image features,multichannel feature classification system,global feature,image segmentation accuracy assessment,feature extraction,image classification,image analysis,feature vector classification,multiple feature space,object recognition,controlled eating event,natural eating event,multiple image segmentation generation,multiple hypothesis image classification,feature selection,stable segmentation selection,automatic food identification,local feature,class decision combination,vectors,medical image processing,classifier feedback,segmented object partitioning,support vector machines,entropy,informatics | Computer vision,Feature vector,Scale-space segmentation,Automatic image annotation,Pattern recognition,Feature detection (computer vision),Computer science,Feature (computer vision),Segmentation-based object categorization,Feature extraction,Image segmentation,Artificial intelligence | Journal |
Volume | Issue | ISSN |
19 | 1 | 2168-2208 |
Citations | PageRank | References |
17 | 0.87 | 39 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Fengqing Zhu | 1 | 209 | 28.06 |
Marc Bosch | 2 | 134 | 8.90 |
Nitin Khanna | 3 | 267 | 24.56 |
Carol J Boushey | 4 | 206 | 20.62 |
Edward J. Delp | 5 | 2321 | 351.37 |