Sentence examples for based on histogram of from inspiring English sources

We compared three commonly used classifiers linear discriminant analysis (LDA) [42], random decision forests (RF) [43] (150 trees), and a SVM [37] (C-SVM, linear kernel with c=1) using three feature representations: PCA, one based on histogram of oriented gradients (HOG) [44, 45], and another based on local binary pattern (LBP) [46, 47] features.

Using the optimal SVT approach above, three image signatures (representations) can be derived: (i) signature (1st) based on histogram of dense-patch SIFT descriptors; (ii) signature (2nd) based on kernel density of dense-patch SIFT descriptors; and (iii) signature (3rd) based on histogram of dense-patch DAISY descriptors.

This paper presents a method based on Histogram of Oriented Gradients to extract features of an image box containing the tracked object and Support Vector Machine to classify moving objects in crowded traffic scenes.

After that, repeating the first step for every test image and encoding them to a single feature vector based on histogram of occurrences of each terms in visual dictionary or storing the statistics of the difference between centers (K-means) or modes (GMM) and each descriptor.

Such approach is based on histograms of optical flow [44], and captures both the local and global information of actions.

Five different implementations are tested against each other and against a control similarity measure based on histograms of class co-occurrence features and the Jensen Shannon divergence.

The experimental validation of the model is based on histograms of Tg distributions which were computed from DSC thermograms by using a new model-based optimisation technique.

In recent years, local image descriptors based on histograms of oriented gradients (e.g., SIFT, DAISY) and intensity orders (e.g., LBP, LIOP) have been popular for the keypoint matching.

Pezzementi et al. [30] apply a predefined exploration routine with a single finger contact, to learn object models based on histograms of features (thus being the closest in data collection methodology to the work presented in this paper).

Based on histograms of the staining for all tumours, the optimal cut-off value for discrimination between negative and positive staining was found to be 1.4.

Single unit discrimination was not routinely possible in these experiments; however, we estimated that recordings at each channel were between one and ten neurons based on histogram analysis of event amplitude and individual firing rates derived from cell-attached and intracellular recordings [14].