面向视频的手指检测算法的研究与实现-计算机技术专业毕业论文.docxVIP

三 三 峡 大 学 全 日 制 专 业 学 位 硕 士 学 位 论 文 PAGE IV万方数据 PAGE IV 万方数据 Abstract Traditional human-machine interaction is limited to the application of keyboard, mouse and joystick for a long time. Although the rage touch screen technology has changed this tradition, the friendly and natural interface still can’t meet people’s requirement. As a natural and intuitive interaction, gesture has been a hot issue for domestic and overseas scholars. However, due to gestures’ diversity, ambiguity and differences between time and space, combined with hand is a complex deformable body, there still hasn’t make a breakthrough progress. Currently, the main drawbacks of Vision-based Gesture Recognition Technology are: (1) low recognition rate; (2) sensitive to scale variance and plane rotation; (3) poor real-time performance. As one of key technologies of gesture recognition, fingertips detection is facing the same problems. Therefore, this article is mainly devoted to explore a fingertip detection algorithm which meets the requirement of detection rate, real-time and robustness on fingers under monocular vision. Then a finger detection system is designed and implemented. On the basis of the prior technology, the works have done in this article are shown as follows: To overcome the deficiencies of the existing fingertip framework, a new fingertip framework is proposed. The framework proposed in this paper realized robustness of the system by introducing palm width information on the basis of the original framework, enhanced the positive detection rate of fingertips by introducing finger width, finger length, and finger orientation information to lower false rate and miss rate which made the system not has high positive detection rate of fingertips, but also has good robustness. For the issues that existing fingertip detection algorithms are sensitive to scale variance and plane rotation, an adaptive fingertip detection algorithm is proposed. Two adaptive fingertip detection