Showing papers on "Quantization (image processing) published in 2022"

Fuzzy vector quantization with a step-optimizer to improve pattern classification

Abstract: The paper proposes a novel supervised algorithm for data classification based on fuzzy vector quantization. The novelty here lies in including an optimization procedure to determine the step size of the quantization process. Adoption of fuzzy space for data exploration eliminates the problem of class-overlapping, while dealing with high dimensional non-linear data. In the proposed approach, the input data are first been transformed from the Euclidean space to the fuzzy space with three membership grades. Next, we have used uniform manifold approximation algorithm (UMAP), for projecting the data in visual space by selection of the most contrasting features from the fuzzy vectors. Then these features are passed through a quantization step with a novel step-optimization technique. Optimizing the quantization step and making it independent of data sets significantly speeds up the process. As the class information of all the feature vectors obtained by UMAP is known, majority voting principle has been used to locate the class-centroids in the subsequent step which in turn represent the class labels of the test samples. In test phase, after obtaining the test vectors, the Hyperspherical Direction Cosines (HDC) between the test vectors and the previously obtained class-centroids are evaluated. The test sample is finally assigned that class label where the sum of absolute differences (SAD) of these direction cosines is minimum. We have validated our classifier on various benchmark data sets and achieved higher accuracy with significantly low computation time than the existing state-of-the-art algorithms.

Compression of image using multi-wavelet techniques

Abstract: Digital compression of images is a topic that has appeared in a lot of studies over the past decade to this day. As wavelet transform algorithms advance and procedures of quantization have helped to bypass current compression of image standards such as the JPEG algorithm. To get the highest effectiveness in compression of image transforms of wavelet need filters which gather a desirable character's number i.e., symmetry and orthogonally. Nevertheless, wave design capabilities are restricted due to their ability to have all of such desirable characters at the same time. The multi-wavelet technology removes a few of the restrictions of the wavelet play more than the options of design and thus able to gather all desired Characters of transforming. Wavelet andmulti-wave filter banks are tested on a larger scale with images, providing more useful analysis. Multiple waves indicate energy-compression efficiency (a higher compression ratio usually indicates a higher mean square error, MSE, in the compressed image). Filter bank Characters such as orthogonal and compact support, symmetry, and phase response are important factors that also affect MSE and professed quality of the image. The current work analyzes the multi-wave Characters effect on the performance of compression of images. Four multi-wavelength Characters (GHM, CL, ORT4) were used in this thesis and the compression of image performance of grayscale images was compared with common scalar waves (D4). SPIHT quantification device in stress chart and use of PSNR and subjective quality measures to assess performance. The results in this paper point out those multi wave characteristics that are most important for the compression of images. Moreover, PSNR results and subjective quality show similar performance to the best scalar and multi-waves. The analysis also shows that a programmer based on multi-band conversion significantly improves the perceived image quality.

Optimized feature space learning for generating efficient binary codes for image retrieval

Abstract: In this paper we propose an approach for learning low dimensional optimized feature space with minimum intra-class variance and maximum inter-class variance. We address the problem of high-dimensionality of feature vectors extracted from neural networks by taking care of the global statistics of feature space. Classical approach of Linear Discriminant Analysis (LDA) is generally used for generating an optimized low dimensional feature space for single-labeled images. Since, image retrieval involves both multi-labeled and single-labeled images, we utilize the equivalence between LDA and Canonical Correlation Analysis (CCA) to generate an optimized feature space for single-labeled images and use CCA to generate an optimized feature space for multi-labeled images. Our approach correlates the projections of feature vectors with label vectors in our CCA based network architecture. The neural network minimize a loss function which maximizes the correlation coefficients. We binarize our generated feature vectors with the popular Iterative Quantization (ITQ) approach and also propose an ensemble network to generate binary codes of desired bit length for image retrieval. Our measurement of mean average precision shows competitive results on other state-of-the-art single-labeled and multi-labeled image retrieval datasets.

Study of compression statistics and prediction of rate-distortion curves for video texture

Abstract: Encoding textural content remains a challenge for current standardised video codecs. It is therefore beneficial to understand video textures in terms of both their spatio-temporal characteristics and their encoding statistics in order to optimize encoding performance. In this paper, we analyse the spatio-temporal features and statistics of video textures, explore the rate-quality performance of different texture types and investigate models to mathematically describe them. For all considered theoretical models, we employ machine-learning regression to predict the rate-quality curves based solely on selected spatio-temporal features extracted from uncompressed content. All experiments were performed on homogeneous video textures to ensure validity of the observations. The results of the regression indicate that using an exponential model we can more accurately predict the expected rate-quality curve (with a mean Bjontegaard Delta rate of .46% over the considered dataset), while maintaining a low relative complexity. This is expected to be adopted by in the loop processes for faster encoding decisions such as rate–distortion optimisation, adaptive quantization, partitioning, etc.

Channel Pruning and Quantization-Based Learning for Object Detection with Computing Source Limited Application

Abstract: With the rise of convolutional neural network (CNN) in the field of computer vision, more and more practical applications need to deploy CNN on mobile devices. However, due to the large amount of CNN computing operations and the large number of parameters, it is difficult to deploy on ordinary edge devices. The neural network model compression method has become a popular technology to reduce the computational cost and has attracted more and more attention. We specifically design a small target detection network for hardware platforms with limited computing resources, use pruning and quantization methods to compress, and demonstrate in VOC dataset and RSOD dataset on the actual hardware platform. Experiments show that the proposed method can maintain a fairly accurate rate while greatly speeding up the inference speed. The proposed model designed in this paper achieves 76.74% mAP on the VOC dataset, which is 4.76 times faster than the original model.