We propose a new objective function for superpixel segmentation. This objective function consists of two components: entropy rate of a random walk on a graph and a balancing term. The entropy rate favors formation of compact and homogeneous clusters, while the balancing function encourages clusters

Abstract. This paper presents a simple and effective nonparametric approach to the problem of image parsing, or labeling image regions (in our case, superpixels produced by bottom-up segmentation) with their categories. This approach requires no training, and it can easily scale to datasets

We present an efficient semantic segmentation algorithm based on contextual information which is constructed us-ing superpixel-level cues. Although several semantic seg-mentation algorithms employing superpixel-level cues have been proposed and significant technical advances have been achieved

noise properties, but they can span multiple distinct image regions, which can degrade the classification performance and make thin obstacles difficult to detect. We address the use of superpixels as the visual primitives for traversability estimation. Superpixels are obtained from an over-segmentation

The sequence of estimates of the speech signal's entropy rate is investigated as a potential basis for speech segmentation. Raising and falling edges of that entropy rate curve and its maxima and minima are considered as candidates for segment boundaries. These prominent points are compared

We propose a new objective function for clustering. This objective function consists of two components: the entropy rate of a random walk on a graph and a balancing term. The entropy rate favors formation of compact and homogeneous clusters, while the balancing function encourages clusters

This study evaluates the potential of the entropy rate contour to identify stationary and non-stationary segments of speech signals. The segmentation produced by an entropy rate-based method is compared to the manual phoneme segmentations of the TIMIT and the KIEL corpora. Characteristic points, i

approach shows the best improvement in F-Measure of 1 % absolute, and the voting approach shows the best reduction in NIST error rate of 2.7 % absolute when compared to the previous best system. Index Terms — sentence segmentation, classifier combination, entropy, lexical and prosodic features, hidden

. In this paper, we propose layers segmentation to detect both moving and stationary target objects from surveillance video. We extend the Maximum Entropy (ME) statistical model to segment layers with features, which are collected by constructing a codebook with a set of codewords for each pixel. We also indicate

We describe a new algorithm for microcalcification segmentation in mammographic X - ray images. The algorithm detects microcalcifications in two steps. First, it removes background tissue with a multiscale morphological operation. Then, it applies entropy thresholding based on a 3-dimensional co