With the rapid development of smart devices, people's lives have become easier, especially for visually disabled or special-needs people. The new achievements in the fields of machine learning and deep learning let people identify and recognise the surrounding environment. In this study, the efficiency and high performance of deep learning architecture are used to build an image classification system in both indoor and outdoor environments. The proposed methodology starts with collecting two datasets (indoor and outdoor) from different separate datasets. In the second step, the collected dataset is split into training, validation, and test sets. The pre-trained GoogleNet and MobileNet-V2 models are trained using the indoor and outdoor se

FG Mohammed, HM Al-Dabbas, Iraqi journal of science, 2018 - Cited by 6

     The searching process using a binary codebook of combined Block Truncation Coding (BTC) method and Vector Quantization (VQ), i.e. a full codebook search for each input image vector to find the best matched code word in the codebook, requires a long time.   Therefore, in this paper, after designing a small binary codebook, we adopted a new method by rotating each binary code word in this codebook into 900 to 2700 step 900 directions. Then, we systematized each code word depending on its angle  to involve four types of binary code books (i.e. Pour when , Flat when  , Vertical when, or Zigzag). The proposed scheme was used for decreasing the time of the coding procedure, with very small distortion per block, by designing s

The effect of using three different interpolation methods (nearest neighbour, linear and non-linear) on a 3D sinogram to restore the missing data due to using angular difference greater than 1° (considered as optimum 3D sinogram) is presented. Two reconstruction methods are adopted in this study, the back-projection method and Fourier slice theorem method, from the results the second reconstruction proven to be a promising reconstruction with the linear interpolation method when the angular difference is less than 20°.

The recent emergence of sophisticated Large Language Models (LLMs) such as GPT-4, Bard, and Bing has revolutionized the domain of scientific inquiry, particularly in the realm of large pre-trained vision-language models. This pivotal transformation is driving new frontiers in various fields, including image processing and digital media verification. In the heart of this evolution, our research focuses on the rapidly growing area of image authenticity verification, a field gaining immense relevance in the digital era. The study is specifically geared towards addressing the emerging challenge of distinguishing between authentic images and deep fakes – a task that has become critically important in a world increasingly reliant on digital med

This article investigates how an appropriate chaotic map (Logistic, Tent, Henon, Sine...) should be selected taking into consideration its advantages and disadvantages in regard to a picture encipherment. Does the selection of an appropriate map depend on the image properties? The proposed system shows relevant properties of the image influence in the evaluation process of the selected chaotic map. The first chapter discusses the main principles of chaos theory, its applicability to image encryption including various sorts of chaotic maps and their math. Also this research explores the factors that determine security and efficiency of such a map. Hence the approach presents practical standpoint to the extent that certain chaos maps will bec

Semantic segmentation is an exciting research topic in medical image analysis because it aims to detect objects in medical images. In recent years, approaches based on deep learning have shown a more reliable performance than traditional approaches in medical image segmentation. The U-Net network is one of the most successful end-to-end convolutional neural networks (CNNs) presented for medical image segmentation. This paper proposes a multiscale Residual Dilated convolution neural network (MSRD-UNet) based on U-Net. MSRD-UNet replaced the traditional convolution block with a novel deeper block that fuses multi-layer features using dilated and residual convolution. In addition, the squeeze and execution attention mechanism (SE) and the s

The high viscosity of heavy oil is a crucial factor that strongly affects its up-stream recovering, down-stream surface transporting and refining processes. Economical methods for recovering the heavy oil and reducing is very important and related to capital and/or operating cost. This research studies the treatment of Iraqi heavy crude oil, which characterize with high viscosity and low API which makes transportation of heavy crude oil a difficult mission, needs for treatment to reduce viscosity for facilitating transportation and processing. Iraqi heavy crude oil was used Sharqi Baghdad, which obtained from Baghdad east oil fields with API 22.2º.Many kinds of additives were used to reduce the viscosity, experiments were performed o