Image Redundancy Reduction for Neural Network Classification Using Discrete Cosine Transforms
نویسندگان
چکیده
High information redundancy and strong correlations in face images result in inefficiencies when such images are used directly in recognition tasks. In this paper, Discrete Cosine Transforms (DCTs) are used to reduce image information redundancy because only a subset of the transform coefficients are necessary to preserve the most important facial features, such as hair outline, eyes and mouth. We demonstrate experimentally that when DCT coefficients are fed into a backpropagation neural network for classification, high recognition rates can be achieved using only a small proportion (0.19%) of available transform components. This makes DCT-based face recognition more than two orders of magnitude faster than other approaches. KeywordsFace recognition, neural networks, feature extraction, discrete cosine transform, data pre-processing.
منابع مشابه
Image Recognition Using Discrete Cosine Transforms as Dimensionality Reduction
Principal Component Analysis (PCA) approaches to image recognition are data dependent and computationally expensive. To classify unknown images they need to match the nearest neighbour in the stored database of extracted image features. In this paper, Discrete Cosine Transforms (DCTs) are used to reduce the dimensionality of image space by truncating high frequency DCT components. The remaining...
متن کاملOptimization of Energy Consumption in Image Transmission in Wireless Sensor Networks (WSNs) using a Hybrid Method
In wireless sensor networks (WSNs), sensor nodes have limited resources with regard to computation, storage, communication bandwidth, and the most important of all, energy supply. In addition, in many applications of sensor networks, we need to send images to a sink node. Therefore, we have to use methods for sending images in which the number and volume of packets are optim...
متن کاملFace Recognition with Radial Basis Function
A generals and an efficient design approach using radial basis function(RBF) neural classifier to cope with small training sets of high dimension , which is a problem frequently encountered in face recognition, is presented in this paper. In order to avoid over fitting and reduce the computational burden, face features are first extracted by the discrete cosine transform method since Principal ...
متن کاملBrain Tumor Classification Using PNN And Clustering
Probabilistic Neural Network (PNN) also termed to be a learning machine is preliminarily used with an extension of various image classifications based on Training networks and Testing networks. To efficiently detect Brain Tumor cells, clustering method based on FCM can also be implemented. The Probabilistic Neural Network (PNN) will be employed to classify the various stages of Tumor cut levels...
متن کاملCompression of a filtered Image using DCT-Technique
Abstract: This paper provides compression of a filtered Image using DISCRETE COSINE TRANSFORM (DCT) and the comparison of PSNR-value between an original Image and noisy Image. Parameters of a given image are Compression Ratio, Number of pixels, Quantization bits per pixel, Frame rate and Correlation between adjacent samples (Φ).These parameters defines the Quality of an image. DCT is better tec...
متن کامل