The new matching score function yields improved performance (in ROC area and hand detection rate) over the Vocabulary Guided Pyramid Match Kernel (VGPMK) and the traditional, rigid HOG distance on American Sign Language video gestured by expert signers. The resulting alignment score is used within a Support Vector Machine hand/not-hand classifier for hand detection. The Histogram of Oriented Gradient (HOG) based matching score function is reformulated to allow non-rigid alignment between pairs of images to account for hand shape variation. In this work, the hand detection problem is addressed in an appearance matching framework. Moreover, the signers’ clothing varies, e.g., skin-toned clothing vs. low-res video gathered by a web cam in a user’s home. Video can be captured under varying illumination, camera resolutions, and levels of scene clutter, e.g., high-res video captured in a studio vs. Hand appearance varies widely across signers due to anthropometric variations and varying levels of signer proficiency. Locating hands in sign language video is challenging due to a number of factors.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |