Search

Face alignment involves locating several facial parts such as eyes, nose and mouth, and has been popularly tackled by fitting deformable models. In this paper, we explore the effect of the combination of structured random regressors and Constrained Local Models (CLMs). Unlike most previous CLMs, we proposed a novel structured random regressors to give a joint prediction rather than pursuing independence while learning the response map for each facial part. In our method, we first present a fast algorithm to learn local graph, which will then be efficiently incorporated into the random regressors. Finally we regularize the output using a global shape model. The benefits of our method are: (i) random regressors allow integration of votes from nearby regions, which can handle various appearance variations, (ii) local graph encodes local geometry and enables joint learning of features of facial parts, (iii) the global model regularizes the result to ensure a plausible final shape. Experimentally, we found our methods to converge easily. We conjecture that structured random regressors can efficiently select good candidate points. Encouraging experimental results are obtained on several publicly available face databases. [ABSTRACT FROM PUBLISHER]

Hand shape recognition is one of the most important techniques used in human-computer interaction. However, it often takes developers great efforts to customize their hand shape recognizers. In this paper, we present a novel method that enables a hand shape recognizer to be built automatically from simple sketches, such as a "stick-figure" of a hand shape. We introduce the Hand Boltzmann Machine (HBM), a generative model built upon unsupervised learning, to represent the hand shape space of a binary image, and formulate the user provided sketches as an initial guidance for sampling to generate realistic hand shape samples. Such samples are then used to train a hand shape recognizer. We evaluate our method and compare it with other state-of-the-art models in three aspects, namely i) its capability of handling different sketch input, ii) its classification accuracy, and iii) its ability to handle occlusions. Experimental results demonstrate the great potential of our method in real world applications. [ABSTRACT FROM PUBLISHER]