SIFT and HOG features for the retrieval of ancient Kannada epigraphs

Abstract

In this work, the authors presented the indexing method for efficient retrieval of Kannada characters. Here the characters were segmented by the connected component method. Then features were extracted by scale invariant feature transform (SIFT) and histogram of oriented gradients (HOG) methods. These features were condensed by principal component analysis. They presented the indexing approach using K‐dimensional tree (K‐D tree) to improve the identification process. For the experiment, they used their own database. The results of the experiment show that the indexing prior is faster than conventional identification approaches in terms of time to script. From experimentation, they observe that fusion features achieve the maximum accuracy of 90% with varying principal component analysis features.

Implementation of Flood Emergency Response System with Face Analytics

“…The image receives an arrow in every pixel by repeating this technique for every pixel in the image. These arrows are known as gradients, and they indicate the transition of light to dark throughout the whole image [11][12][13][14][15][16][17][18][19][20]. The upper right most section of the pie charts shows the flood duration in days.…”

“…The binning process transforms block normalization into a single-cell normalization that is done in the Step 4. Step 5 involves the HOG feature vector and Scale Invariant and Feature Transform (SIFT) algorithm to search the similar features and save into a database [20].…”

Based on the Inception and the ResNet Module Improving VGG16 to Classify Commodity Images

“…is the total loss function, and z (l) j is the output of the j th node in the l th layer. The gradient loss function of the l th layer is shown in formula (1).…”

“…Assuming that the batch is a set of m training data x (1) , y (1) , • • • , x (m) , y (m) . The loss function is shown in formula (3).…”

“…So automatic acquisition of commodity categories has become a hot research direction combining image processing technology and retail industry. The traditional image classification algorithm is mainly divided into two stages: the first stage adopts the traditional SIFT feature operator [1][2][3] and HOG feature operator [1][2][3] and other artificially designed feature algorithms to extract the image features; In the second stage, support vector machine [4] (SVM) and other classifiers are used for classification. Ke Xiao et al [5] realized the classification and retrieval of flower images by using the image multi-feature and support vector machine method.…”