K. Ribana ¹, S. Pradeep ¹, B. Nandhini ¹

Affiliations
1 Department of Electronics and Communication Engineering, M. Kumarasamy College of Engineering, Karur – 639113,Tamil Nadu, IN

Abstract

Objectives: To design the hardware architecture for contrast enhancement applications. Methods / Statistical Analysis: Image improvement is the technique utilized to make strides the visible illustration of an image. Histogram equalization is one of the most vital techniques of image improvement. Findings: The fundamental idea of histogram equalization is to re-map the gray degrees of the image. Indeed in spite of the fact that these approaches may improve the differentiate of a picture in a successful and proficient way, they ordinarily have a few downsides, like misfortune in data, commotion enhancement and over enhancement. In this extend a modern strategy which performs differentiate improvement may named as adjusted color protecting versatile gamma adjustment. The upgrade is gotten by a combination of altered histogram and its versatile gamma adjustment. Applications / Imporovement:The proposed strategy is analyzed for many differentiate test pictures. It works better than existing. In addition to that the VLSI architecture of the algorithm is developed for size 2×2 image using ALTERA QUARTUS II. The same architecture can be extended to entire image.

Keywords

Altera Quartus II, Minimum Mean Brightness Error , Over Enhancement

Full Text

   

S. Pradeep ¹, B. Nandhini ¹, K. Ribana ¹

Affiliations
1 Department of Electronics and Communication Engineering, M. Kumarasamy College of Engineering, Karur – 639113, Tamil Nadu, IN

Abstract

Objective: The decoder dynamic power consumption has to be reduced. Delay in decoding must be reduced with lesser area. Better area consumption is one main objective of the Hi ECC technique. Methods/Statistical Analysis: Logarithmic delicate choice translating of Reed-Solomon codes can significant coding pick up with polynomial multifaceted nature. Especially, the low intricacies pursue (LCC) ASD interpreting has better execution many-sided quality exchange off. The test vectors should be added over and a polynomial determination conspire should be utilized to choose one introduction yield to send rest deciphering steps. Findings: In this technique RS codes are utilized for simplification. So improvements are proposed for a low many-sided quality polynomial determination plot. At that point introduction plot is produced to make disentangled polynomial determination by just chose vectors are interjected over. Two introductions can be brought together in single emphasis. To lessen dormancy parallel interpolator is utilized to get various yields and enhance speed. Application/Improvements: Data rate is reduced from 12Mbps to 1.1 Mbps. Encoder needs less computation time than decoder. Less computation time of decoder has to be considered for the improvement.

Keywords

Decoding, High Speed, Interpolation, Low Complexity, RS Coder, LCC Decoding

Full Text

   

B. Nandhini ¹, K. Ribana ¹, S. Pradeep ¹

Affiliations
1 Department of ECE, M. Kumarasamy College of Engineering, Karur – 639113, Tamil Nadu, IN

Abstract

Objectives: To propose an algorithm for Medical image retrieval better. Methods/Statistical analysis: The proposed image retrieval system incorporates with methods like discrete wavelet transform, information gain and the convolutional neural network for classification. Findings: We propose an algorithm of image retrieval that implements the feature extraction with 2D-Discrete Wavelet Transform (DWT), information gain for feature reduction and convolutional neural network for classification. The feature extraction involves the extraction of features from medical image using DWT. The Feature reduction was carried out by information gain. The image is classified by using classifiers such as convolutional neural network, traditional SVM classifier and KNN classifier. Application/Improvements: The classifier result provides the similar images in the database. The classification accuracy of convolutional neural network is 91.25% outperforms the traditional SVM classifier and KNN classifier. The image retrieved on high accuracy classifier provides exact match of query medical image for the diagnosis and treatment schedule.

Keywords

Convolutional Neural Network, Discrete Wavelet Transform, Information Gain, KNN Classifier, Medical Image Retrieval

Full Text