Sharif Digital Repository

The objective of OCR systems is to retrieve machine-encoded text from a raster image. Despite the abundance of powerful OCR algorithms for English, there are not many for Farsi. Our proposed algorithm is comprised of pre-processing, line detection, sub-word detection and segmentation, feature extraction and classification. Furthermore, hardware implementation and acceleration of this system on a GPGPU is presented. This algorithm was tested on 5 fonts including Titr, Lotus,Yekan, Koodak and Nazanin and an average accuracy above 90% was achieved  

Many mobile applications running on smartphones, wearable devices, tiny autonomous robots and IoT devices would potentially benefit from the accuracy and scalability of deep CNN-based machine learning algorithms. However,performance and energy consumption limitations make the execution of such computationally intensive algorithms on embedded mobile devices prohibitive.We present a GPU-accelerated engine, dubbed mCNN, for execution of trained deep CNNs on mobile platforms. The proposed solution takes the trained model as input and automatically optimizes its parallel implementation on the target mobile platform for efficient use of hardware resources such as mobile GPU threads and SIMD units.... 

Spiking Neural Networks(SNN) are networks which are consisted of layers of neurons, like other typical artificial neural networks. The main difference between SNN and other neural networks is the type of data transportation among neurons which is done by spikes. Spiking neural networks and their models are considered as the nearest networks and neurons to animals’ nervous systems. In aspects of hardware implementation, the type of data transportation in SNN causes them to be ultra-low power. So, implementation of these networks on chips like FPGA and also usage of SNN in applications with high processing load have startling germination, recently. In this work, we have tried to propose some... 

Many chip manufacturers have recently introduced high-performance deep-learning hardware accelerators. In modern GPUs, programmable tensor cores accelerate the heavy operations involved in deep neural networks. This paper presents a novel solution to re-purpose tensor cores in modern GPUs for high-throughput implementation of turbo decoders. Turbo codes closely approach Shannon’s limit on channel capacity, and are widely used in many state-of-the-art wireless systems including satellite communications and mobile communications. Experimental evaluations show that the proposed solution achieves about 1.2 Gbps throughput, which is higher compared to previous GPU-accelerated solutions  

There have been many works on generative networks and image generation in the past few years, but the problem with this work is that there is no control over the generated images. The goal of disentangled image synthesis is to generate new images with specific detail and have control over the generated images. Image-based virtual try-on aims to synthesize the customer image with an in-shop clothes image to acquire seamless and natural try-on results, which have attracted increasing attention. The main procedures of image-based virtual try-on usually consist of clothes image generation and try-on image synthesis. In contrast, prior arts cannot guarantee satisfying clothes results when facing... 

In this project, a method is emoloyed to implement a Viterbi decoder on GPGPU. This method is based on combining all steps of the algorithm. This combination has some challenges that are related to differences between different steps of the algorithm. So in this project, some solutions are found to handle these challenges and a high-throughput Viterbi decoder is acheived  

In this study, utilizing the so-called “flow forming”, a cold-bonding process is developed to produce multi-layered thin-walled tubes and cylinders. In this process, which is entitled as “spin-bonding”, two layers of tubes are bonded by thickness reduction. Al/Al and Cu/Al tubes were bonded at various temperatures, thickness reductions, feed rates and roller attack angles. The bonding quality was examined by peel test, metallography and SEM fractography. Moreover, spin-bonding was accumulatively applied to aluminum tubes up to 4 cycles as a severe plastic deformation (SPD) for thin-walled tubes and cylinders entitled as “Accumulative Spin-Bonding” (ASB). Beside of experimental works,... 

Combination of 3D stacking and network-on-chip (NoC), known as 3D NoC, has some advantages such as reduced propagation delay, chip area and interconnect, and power consumption, and bandwidth increase. Despite these advantages, the increased power density per chip area due to area decrease causes thermal problems in 3D NoCs to be more critical than 2D NoCs. Therefore, design of temperature management algorithms is essential for these systems. One of the dynamic thermal management techniques is task migration that balances generated thermal among cores.In this thesis, we propose a task migration scheme using feedback control for 3D NoCs. The main purpose of this scheme is to decrease the peak... 

Amount of strain has been always considered as the primary parameter affecting the microstructural and strength evolutions during Severe Plastic Deformation (SPD). However, these evolutions unavoidably saturate in large strains under deformation with constant conditions, i.e. constant deformation temperature, strain rate and strain path. In this study, effects of these factors on the microstructural and flow behavior of Ultra-Fine Grain (UFG) aluminum (AA 1050 and AA 5052) processed by Accumulative Roll-Bonding (ARB) are investigated. The flow behavior and its time-dependent aspect are evaluated up to large strains by Plane Strain Compression (PSC) and Stress Relaxation (SR) tests. ...