LIME-Based Data Selection Method for SAR Images Generation Using GAN

Deep learning has obtained remarkable achievements in computer vision, especially image and video processing. However, in synthetic aperture radar (SAR) image recognition, the application of DNNs is usually restricted due to data insufficiency. To augment datasets, generative adversarial networks (GANs) are usually used to generate numerous photo-realistic SAR images. Although there are many pixel-level metrics to measure GAN’s performance from the quality of generated SAR images, there are few measurements to evaluate whether the generated SAR images include the most representative features of the target. In this case, the classifier probably categorizes a SAR image into the corresponding class based on “wrong” criterion, i.e., “Clever Hans”. In this paper, local interpretable model-agnostic explanation (LIME) is innovatively utilized to evaluate whether a generated SAR image possessed the most representative features of a specific kind of target. Firstly, LIME is used to visualize positive contributions of the input SAR image to the correct prediction of the classifier. Subsequently, these representative SAR images can be selected handily by evaluating how much the positive contribution region matches the target. Experimental results demonstrate that the proposed method can ally “Clever Hans” phenomenon greatly caused by the spurious relationship between generated SAR images and the corresponding classes.

Performance Evaluation of Digital Image Processing by Using Scilab

Scilab is an open-source, cross-platform computational environment software available for academic and research purposes as a free of charge alternative to the matured computational copyrighted software such as MATLAB. One of important library available for Scilab is image processing toolbox dedicated solely for image and video processing. There are three major toolboxes for this purpose: Scilab image processing toolbox (SIP), Scilab image and video processing toolbox (SIVP) and recently image processing design toolbox (IPD). The target discussion in this paper is SIVP due to its vast use out there and its capability to handle streaming video file as well (note that IPD also supports video processing). Highlight on the difference between SIVP and IPD will also be discussed. From testing, it is found that in term of looping test, Octave and FreeMat are faster than Scilab. However, when converting RGB image to grayscale image, Scilab outperform Octave and FreeMat.

Rectangling irregular videos by optimal spatio-temporal warping

Image and video processing based on geometric principles typically changes the rectangular shape of video frames to an irregular shape. This paper presents a warping based approach for rectangling such irregular frame boundaries in space and time, i.e., making them rectangular again. To reduce geometric distortion in the rectangling process, we employ content-preserving deformation of a mesh grid with line structures as constraints to warp the frames. To conform to the original inter-frame motion, we keep feature trajectory distribution as constraints during motion compensation to ensure stability after warping the frames. Such spatially and temporally optimized warps enable the output of regular rectangular boundaries for the video frames with low geometric distortion and jitter. Our experiments demonstrate that our approach can generate plausible video rectangling results in a variety of applications.

A Double Bit Approximate Adder Providing a New Design Perspective for Gate-Level Design

In the modern Block-chain and Artificial Intelligence era, energy efficiency has become one of the most important design concerns. Approximate computing is a new and an evolving field promising to provide energy-accuracy trade-off. Several applications are tolerant to small degradation in results, and hence tasks like image and video processing are candidates to benefit from Approximate Computing. In this paper, we propose a new design approach for designing approximate adders and further optimize the accuracy and cost metrics. Our approach is based on minimizing the errors while cascading more than one 1-bit adder. We insert [Formula: see text] on specific locations to achieve a reasonable circuit minimization and reduce the [Formula: see text] cost. We compare our design with exact adder and relevant state-of-the-art approximate adders. Through analysis and simulations, we show that our approach provides higher accuracy and far better performance compared with other designs. The proposed double bit approximate adder provides more than 25% savings in gate count compared with the exact adder, has a mean absolute error of 0.25 which is lowest among all the reference approximate adders and reduces the power-delay product by more than 60% compared to the exact adder. When employed for image filtering, the proposed design provides a [Formula: see text] of 96%, a [Formula: see text] of 95% and a [Formula: see text] of 91% relative to the actual results, while the second best approximate adder only achieves 64%, 54% and 71% of these image quality metrics, respectively.

Face Detection and Recognition Using OpenCV

Intel's OpenCV is a free and open-access image and video processing library. It is linked to computer vision, like feature and object recognition and machine learning. This paper presents the main OpenCV modules, features, and OpenCV based on Python. The paper also presents common OpenCV applications and classifiers used in these applications like image processing, face detection, face recognition, and object detection. Finally, we discuss some literary reviews of OpenCV applications in the fields of computer vision such as face detection and recognition, or recognition of facial expressions such as sadness, anger, happiness, or recognition of the gender and age of a person.