From the Publisher: 
The accessible presentation of this book gives both a general view of the entire computer vision enterprise and also offers sufficient detail to be able to build useful applications. Users learn techniques that have proven to be useful by first-hand experience and a wide range of mathematical methods. A CD-ROM with every copy of the text contains source code for programming practice, color images, and illustrative movies. Comprehensive and up-to-date, this book includes essential topics that either reflect practical significance or are of theoretical importance. Topics are discussed in substantial and increasing depth. Application surveys describe numerous important application areas such as image based rendering and digital libraries. Many important algorithms broken down and illustrated in pseudo code. Appropriate for use by engineers as a comprehensive reference to the computer vision enterprise.

Computer vision : a modern approach = 计算机视觉 : 一种现代的方法

International Journal of Computer and Applications

MUCKE aims to mine a large volume of images, to structure them conceptually and to use this conceptual structuring in order to improve large-scale image retrieval. The last decade witnessed important progress concerning low-level image representations. However, there are a number problems which need to be solved in order to unleash the full potential of image mining in applications. The central problem with low-level representations is the mismatch between them and the human interpretation of image content. This problem can be instantiated, for instance, by the incapability of existing descriptors to capture spatial relationships between the concepts represented or by their incapability to convey an explanation of why two images are similar in a content-based image retrieval framework. We start by assessing existing local descriptors for image classification and by proposing to use co-occurrence matrices to better capture spatial relationships in images. The main focus in MUCKE is on cleaning large scale Web image corpora and on proposing image representations which are closer to the human interpretation of images. Consequently, we introduce methods which tackle these two problems and compare results to state of the art methods. Note: some aspects of this deliverable are withheld at this time as they are pending review. Please contact the authors for a preview.

http://ieeexplore.ieee.org/iel2/4524/12820/00592460.pdf

Image Processing

IEEE Transactions on Pattern Analysis and Machine Intelligence

Deep Convolutional Neural Network (CNN) is a special type of Neural Networks, which has shown exemplary performance on several competitions related to Computer Vision and Image Processing. Some of the exciting application areas of CNN include Image Classification and Segmentation, Object Detection, Video Processing, Natural Language Processing, and Speech Recognition. The powerful learning ability of deep CNN is primarily due to the use of multiple feature extraction stages that can automatically learn representations from the data. The availability of a large amount of data and improvement in the hardware technology has accelerated the research in CNNs, and recently interesting deep CNN architectures have been reported. Several inspiring ideas to bring advancements in CNNs have been explored, such as the use of different activation and loss functions, parameter optimization, regularization, and architectural innovations. However, the significant improvement in the representational capacity of the deep CNN is achieved through architectural innovations. Notably, the ideas of exploiting spatial and channel information, depth and width of architecture, and multi-path information processing have gained substantial attention. Similarly, the idea of using a block of layers as a structural unit is also gaining popularity. This survey thus focuses on the intrinsic taxonomy present in the recently reported deep CNN architectures and, consequently, classifies the recent innovations in CNN architectures into seven different categories. These seven categories are based on spatial exploitation, depth, multi-path, width, feature-map exploitation, channel boosting, and attention. Additionally, the elementary understanding of CNN components, current challenges, and applications of CNN are also provided.

https://link.springer.com/content/pdf/10.1007/s10462-020-09825-6.pdf

A survey of the recent architectures of deep convolutional neural networks

In this paper a comparative analysis on various aerial image enhancement techniques are carried out with that of wavelet based enhancement technique based on certain quality assessments. Paper illustrates wavelet based enhancement algorithm performed in an intelligent manner and the obtained result is compared with other conventional enhancement techniques. From the comparative analysis performed using mean square error, peak signal to noise ratio and structured similarity index measurement the wavelet based enhancement technique is found to give better enhancement result. Since the algorithms proposed are applicable to color images this work can be further extended to other applications like feature extractions of roads and buildings, medical image segmentation and video streaming.

Comparative Analysis on Aerial Image Enhancement Techniques

This paper presents a novel technique for designing an Infinite Impulse Response (IIR) Filter with Linear Phase Response. The design of IIR filter is always a challenging task due to the reason that a Linear Phase Response is not realizable in this kind. The conventional techniques involve large number of samples and higher order filter for better approximation resulting in complex hardware for implementing the same. In addition, an extensive computational resource for obtaining the inverse of huge matrices is required. However, we propose a technique, which uses the frequency domain sampling along with the linear programming concept to achieve a filter design, which gives a best approximation for the linear phase response. The proposed method can give the closest response with less number of samples (only 10) and is computationally simple. We have presented the filter design along with its formulation and solving methodology. Numerical results are used to substantiate the efficiency of the proposed method.

A Novel Methodology for Designing Linear

Software Defined Radio or SDR is basically a radio functionality implemented in software. Going into the subtleties of an SDR, we can find that there is a hardware component to serve the purpose of an RF front end, without which a radio is non-functional. GNURadio Companion serves as the software end to which the hardware is attached. There have been advances in the hardware end over the years and this paper serves to compare the different hardware counterparts of the GNURadio companion. We have taken hardwares extending from the high cost series of Universal Software Radio Peripherals (USRPs) to medium cost FUNcube Dongle (FCD) to the extremely low cost RTL-SDR dongle.

Hardware Companions to the GNU Radio Companion: A comparative study of Software Radio Hardwares

The novelty of this paper is edge detection in binary and color images using the Ricci curvature function is proposed. The reason for this is, if the edges in an image are determined accurately, then all of the objects can be located and basic image properties can be measured. In this paper we represent images as a manifold and make use of differential geometry in image processing, namely the Ricci curvature. Over the conventional edge detection methods Canny edge detector is the best available. So, we attempted a visual comparison of edge detection on digital image with Canny detector and Ricci curvature function. We demonstrate some features that can be added or missed in binary images by the Canny edge detector and the registration of edges in color images by the Ricci method.

Binary and Color Image Edge Detection Using RicciFlow

Abstract. Dense Residual U-Net (DRU-Net) is a neural network used for image segmentation. It is based on the U-Net architecture and isa combination of modified ResNet as the encoder and modified DenseNet as the decoder blocks. DRU-Net captures both the local and contextual information. Previous studies on DRU-Net have not tested the influence of the spectral resolution of the images. In an earlier study, the DRU-Net was trained with grayscale images for epiphyte segmentation. The network trained and tested with grayscale images underperformed while varying the illumination and occupancy of the target in the frame. In this study, the same network was trained and tested with RGB images for assessing the increase in overall learning. The performance of the network in segmenting epiphytes under conditions such as good/poor illumination and high/low target occupancy was analyzed. Dice and Jaccard scores were used as evaluation metrics. The DRU-Net model trained with RGB images had an improvement of 20% over the grayscale model in both average Dice and average Jaccard scores of the target class. Based on the higher Dice and Jaccard scores, adding additional spectral information improves DRU-Net learning. The increased computation time required for training DRU-Net with RGB images will result in better output. This model could be further used for identifying multiple epiphytes in images with poor illumination and different occupancy conditions.


/pdf/influence-of-additional-spectral-bands-for-epiphyte-s78lpzmi.pdf

K. P. Soman

Papers

Comparative Analysis on Aerial Image Enhancement Techniques

A Novel Methodology for Designing Linear

Hardware Companions to the GNU Radio Companion: A comparative study of Software Radio Hardwares

Binary and Color Image Edge Detection Using RicciFlow

Influence of additional spectral bands for epiphyte segmentation on dru-net