Quantization (image processing)

About: Quantization (image processing) is a research topic. Over the lifetime, 7977 publications have been published within this topic receiving 126632 citations.

High-dynamic-range still-image encoding in JPEG 2000

Abstract: The raw size of a high-dynamic-range (HDR) image brings about problems in storage and transmission. Many bytes are wasted in data redundancy and perceptually unimportant information. To address this problem, researchers have proposed some preliminary algorithms to compress the data, like RGBE/XYZE, OpenEXR, LogLuv, and so on. HDR images can have a dynamic range of more than four orders of magnitude while conventional 8-bit images retain only two orders of magnitude of the dynamic range. This distinction between an HDR image and a conventional image leads to difficulties in using most existing image compressors. JPEG 2000 supports up to 16-bit integer data, so it can already provide image compression for most HDR images. In this article, we propose a JPEG 2000-based lossy image compression scheme for HDR images of all dynamic ranges. We show how to fit HDR encoding into a JPEG 2000 encoder to meet the HDR encoding requirement. To achieve the goal of minimum error in the logarithm domain, we map the logarithm of each pixel value into integer values and then send the results to a JPEG 2000 encoder. Our approach is basically a wavelet-based HDR still-image encoding method.

An embedded wavelet hierarchical image coder

Abstract: A simple, yet remarkably effective, image compression algorithm that has the property that the bits in the bit stream are generated in order of importance, yielding fully hierarchical image compression suitable for embedded coding or progressive transmission, is described. Given an image bit stream, the decoder can cease decoding at the same image that would have been encoded at the bit rate corresponding to the truncated bit stream. The compression algorithm is based on three key concepts: (1) wavelet transform or hierarchical subband decomposition, (2) prediction of the absence of significant information across scales by exploiting the self-similarity inherent in images, and (3) hierarchical entropy-coded quantization. >

Deep Visual-Semantic Quantization for Efficient Image Retrieval

Abstract: Compact coding has been widely applied to approximate nearest neighbor search for large-scale image retrieval, due to its computation efficiency and retrieval quality. This paper presents a compact coding solution with a focus on the deep learning to quantization approach, which improves retrieval quality by end-to-end representation learning and compact encoding and has already shown the superior performance over the hashing solutions for similarity retrieval. We propose Deep Visual-Semantic Quantization (DVSQ), which is the first approach to learning deep quantization models from labeled image data as well as the semantic information underlying general text domains. The main contribution lies in jointly learning deep visual-semantic embeddings and visual-semantic quantizers using carefully-designed hybrid networks and well-specified loss functions. DVSQ enables efficient and effective image retrieval by supporting maximum inner-product search, which is computed based on learned codebooks with fast distance table lookup. Comprehensive empirical evidence shows that DVSQ can generate compact binary codes and yield state-of-the-art similarity retrieval performance on standard benchmarks.

The spatial relationship of DCT coefficients between a block and its sub-blocks

Abstract: At present, almost all digital images are stored and transferred in their compressed format in which discrete cosine transform (DCT)-based compression remains one of the most important data compression techniques due to the efforts from JPEG In order to save the computation and memory cost, it is desirable to have image processing operations such as feature extraction, image indexing, and pattern classifications implemented directly in the DCT domain To this end, we present in this paper a generalized analysis of spatial relationships between the DCTs of any block and its sub-blocks The results reveal that DCT coefficients of any block can be directly obtained from the DCT coefficients of its sub-blocks and that the interblock relationship remains linear It is useful in extracting global features in the compressed domain for general image processing tasks such as those widely used in pyramid algorithms and image indexing In addition, due to the fact that the corresponding coefficient matrix of the linear combination is sparse, the computational complexity of the proposed algorithms is significantly lower than that of the existing methods

Color image watermarking using quaternion Fourier transform

Abstract: The paper presents a digital color image watermarking scheme using a hypercomplex numbers representation and the quaternion Fourier transform (QFT). Previous color image watermarking methods are first presented and the quaternion representation is then described. In this framework, RGB pixel values are associated with a unique quaternion number having three imaginary parts. The QFT is presented; this transform depends on an arbitrary unit pure quaternion, /spl mu/. The value of /spl mu/ is selected to provide embedding spaces having robustness and/or perceptual properties. In our approach, /spl mu/ is a function of the mean color value of a block and a perceptual component. A watermarking scheme based on the QFT and the quantization index modulation scheme is then presented. This scheme is evaluated for different color image filtering processes (JPEG, blur). The fact that perceptive QFT embedding can offer robustness to luminance filtering techniques is outlined.