China
Africa
Explore chapters and articles related to this topic
Genetic Optimization of Feature Representation for Compressed-Domain Image Categorization
Published in Kim-Hui Yap, Ling Guan, Stuart William Perry, Hau-San Wung, Adaptive Image Processing, 2018
Kim-Hui Yap, Ling Guan, Stuart William Perry, Hau-San Wung
Typically, in the spatial domain, a color histogram is constructed based on the occurrence frequencies of particular color intensities by scanning the image pixel by pixel. Similarly, in the compressed domain, we can construct a DCT coefficient histogram [200] by directly accessing the compressed-domain coefficients. In order to obtain the coefficient values from the DCT blocks, we first have to perform the Huffman decoding, de-zigzagging and dequantization [218,220] on the encoded data of the compressed images. These steps are fast and computationally inexpensive compared with the IDCT step. Given a DCT-based JPEG compressed image with n 8 × 8 DCT coefficient blocks, the histogram of a specific coefficient can be constructed easily by counting the occurrence frequency of a particular coefficient value in these n DCT coefficient blocks. In other words, we are essentially modeling the chosen DCT coefficient as a random variable, and consider the histogram as an approximation of the variable’s associated probability mass function (pmf).
Vehicle association among multiple cameras
Published in Amir Hussain, Mirjana Ivanovic, Electronics, Communications and Networks IV, 2015
Hao Sheng, Xing Zhang, Chao Li, Zhang Xiong
In our framework, we use two features, ASIFT and color histogram. ASIFT simulates a set of sample views of the initial images, they are obtained by varying the two camera axis orientation parameters, namely the latitude and the longitude angles. Then it applies the SIFT method (Lowe 2004) itself to all images thus generated. Thus, ASIFT covers all six parameters of the affine transform effectively. And, against any prognosis, simulating a large enough set of sample views depending on the two cameras' orientation parameters is feasible with no dramatic computational load. Color histogram (Han & Ma 2002) is a representation of the distribution of colors in an image. For digital images, a color histogram represents the number of pixels that have colors in each of a fixed list of color ranges, which spans the image's color space, the set of all possible colors.
Feature Extraction and Learning for Visual Data
Published in Guozhu Dong, Huan Liu, Feature Engineering for Machine Learning and Data Analytics, 2018
Parag S. Chandakkar, Ragav Venkatesan, Baoxin Li
A color histogram is largely invariant to smaller changes in lighting and viewpoint. It can be computed in linear time, making it an effective feature for applications such as image retrieval [3,4,63]. On the other hand, its effectiveness depends on the binning strategy. For example, bins derived from a large collection of natural images are unlikely to work well for a fundus image shown in Figure 3.1 that has a predominantly red spectrum. A certain amount of hand-crafting is required to adapt the histogram to fundus images. To automatically derive the quantization bins for any dataset (assuming that it has sufficient number of samples), one can extract all the unique shades (i.e., RGB triplets) from the dataset and perform k-means clustering on them. The centroids can then be viewed as histogram bins. This approach was proposed in [59]. It produces a histogram that has more entropy than the one derived using bins based on natural images. Figure 3.2 shows a color histogram of the landscape image that uses pre-defined bins suitable for natural images. It also shows a color histogram of the fundus image using the same binning strategy. This binning strategy does not capture the color distribution in the fundus image well. By using this adaptive binning strategy, one may obtain a better histogram as shown in Figure 3.3 [10,11,59]. The obtained histogram has a higher entropy as it makes better utilization of the available number of bins. In practice, it has been observed that the adaptive binning strategy allows us to use fewer bins (e.g., 16 instead of 64) with almost no loss of performance [10,11,59].
An image authentication technology based on depth residual network
Published in Systems Science & Control Engineering, 2018
Jiafa Mao, Danhong Zhong, Yahong Hu, Weiguo Sheng, Gang Xiao, Zhiguo Qu
The colour histogram can be obtained by counting the number of occurrences of each colour in the image matrix. The histogram is invariant to the translation and rotation of the image plane, and the change is very slow at the change of the viewing angle. The colour histogram H of a given image is defined as a vector: where “i” is the colour in the colour histogram, H [i] represents the number of pixels in the HSV colour in the image, and N is the dimension in the colour histogram. To compare histograms with different sizes, the colour histogram needs to be normalized. The formula for colour histogram normalization is as follows (Jasmine & Kumar, 2014): where P represents the total number of pixels in the image. After the colour histogram is normalized, the colour difference between the images can be compared by the method of histogram intersections, distance and centre distance.
Boosting the multiple aircraft online tracking performance via enriching the associated data with fused targets features
Published in International Journal of Image and Data Fusion, 2023
A. M. Awed, Ali Maher, Mohammed A. H. Abozied, Yehia Z. Elhalwagy
The colour histogram is usually used to represent colour distribution of the input image by searching colour space and counting pixels number for each colour zone, and it can work on all colour space like RGB, HSV (Roy and Mukherjee 2013). Based on our survey detection accuracy can be improved by combining colour histogram features with shape-based features like HOG or other shape detectors. For the proposed method the HOG contextual shape descriptor is combined with the colour histogram feature to enrich target appearance information for the data association.