The importance of Satellite Aperture Radar (SAR) imagery systems is increasing day-by-day in various field such as earth observation, hi-technology war mechanisms, etc. The images captured by SAR imagery systems are mainly used to detect and classify objects captured in the images. Due to the complexity of the image capturing process, SAR images can be highly noisy – often consisting of multiplicative noise, also known as speckle. To detect or classify objects in SAR images, speckle noise must be removed from images. During despeckling process, the preservation of important information in the SAR images while removing noise such as edge or patterns is a crucial task. Despeckling methods are liable to compromise on edge preservation ability while aspiring for good quality denoised images. Many researchers have proposed wavelet transform based despeckling approaches such as Discrete Wavelet Transform (DWT), Undecimated Wavelet Transform (UDWT), Dual Tree Complex Wavelet Transform (DTCWT). In these approaches, finding the best values of the coefficients plays an important role in yielding excellent denoised images with preserved edges. In this paper, we have proposed a novel optimization framework that optimizes thresholding coefficients of DTCWT despeckling method for SAR images. The proposed optimization framework is based on Fruit Fly Optimization (FOA) algorithm. The approach is a multi-objective optimization algorithm that is used to find maximum values for Peak Signal-to-Noise Ratio (PSNR), Mean Structural Similarity Index (MSSIM) and Equivalent number of look (ENL). The maximum value of MSSIM indicates high edge preservation capacity, whereas maximum PSNR value indicates good quality denoising of images. The maximum ENL value represents a good speckle-noise smoothing capability. We have applied our framework over some classical images as well as over SAR images of MSTAR dataset. In our experiments, we found that our proposed framework results in the excellent PSNR 36.87 dB, 35.4 dB and 37.8 dB, MSSIM values 0.92, 0.93 and 0.92, respectively, in the case of lena image, MSTAR dataset image and TerraSAR-X dataset image.
1 January 2022 in International Journal of Social Ecology and Sustainable Development
Because of the capacity to work at any climate circumstance and infiltration ability through the clouds and soil, SAR (Synthetic Aperture Radar) imagery has been very demanding.SAR imagery system captures images from any satellite or moving object such as aircraft etc. As per the height of a RADAR system increases the resolution of SAR images is also increased. Due to high-resolution images and multiplicative noise known as speckle, it is not easy to analyze these images. So, it has become very important to remove speckle from these images.There are great numbers of de-speckling techniques have been proposed in past. It is very difficult to identify a suitable technique for a de-speckling task. In this article, authors have proposed a literature survey of some techniques.Authors compared best techniques based on their merits and the different parameters used so far for the observation of SAR images. In recent years, the popularity of deep learning has grown tremendously. For de-speckling of SAR images, various improved CNNs and deep learning based approaches have been proposed.
Car recognition systems have been gaining popularity in recent years due to their ability to identify the make, model, and year of cars from images. In this paper, we present the building of accurate car recognition systems by using neural networks. This paper proposes a car recognition system using the convolution neural network and VMMRdb dataset and the ResNet-152 model, which provides state-of-the-art performance in image classification tasks. The performance of the proposed model is compared with the GG16 model. The experimental results show that the developed car recognition system achieved high accuracy of 54.4% and efficiency in identifying the cars which has important applications in traffic analysis, theft prevention, and marketing research. We also compared the performance of our model with that of other state-of-the-art car recognition systems, including the popular VGG16 model. This object recognition system has practical applications in various fields, such as law enforcement, parking access control, and traffic monitoring, and can help identify stolen or wanted vehicles quickly and efficiently.