قنبری سرخی, علی
دانشگاه صنعتی شاهرود
[ 1 ] - انتخاب ناحیه‌های کاندید در سیستم‌های تشخیص و شناسایی اشیاء
According to the studies carried out in recent years, determination of the regional proposal is one of the crucial steps in detection and recognition of the objects included in an image. In fact, determination of this region has been like a bottleneck, gaining a significant computational energy. As a result, selection of suitable and fast approaches, under these circumstance, may enhance the pe...
[ 2 ] - تشخیص و فیلترینگ هوشمند تصاویر نامتعارف به‌کمک شبکه‌های عصبی عمیق
Currently vast improvement of internet access and significant growth of web based broadcasters have resulted in distribution and sharing of informative resources such as images worldwide. Although this kind of sharing may bring many advantages, there are certain risks such as access of kids to porn images which should not be neglected. In fact, access to these images can be a threat to the cult...
[ 3 ] - People Re-identification in Non-overlapping Field-of-views using Cumulative Brightness Transform Function and Body Segments in Different Color Spaces
Non-overlapping field-of-view (FOV) cameras are used in surveillance system to cover a wider area. Tracking in such systems is generally performed in two distinct steps. In the first step, people are identified and tracked in the FOV of a single camera. In the second step, re-identification of the people is carried out to track them in the whole area under surveillance. Various conventional fea...
[ 4 ] - بهبود شبکه عمیق R-FCN در آشکارسازی و برچسبزنی اشیاء
امروزه آشکارسازی و برچسبزنی اشیاء در تصاویر یکی از چالشهای اساسی در برخی از کاربردهای بیناییماشین میباشد. در سالهای اخیر استفاده از یادگیری عمیق مورد توجه محققان قرار گرفته است. در همین راستا، در این مقاله ابتدا جدیدترین شبکه‌های عمیق موجود معرفی، سپس نقاط قوت و ضعف آنها تحلیل می‌شود. در ادامه شبکهای بهبود یافته از شبکه R-FCN ارائه می‌شود. روش پیشنهادی بر پایه معماری ResNet و شبکه تمام کا...
Co-Authors