PDF(Pubmed)
Abstract：
Accurately extracting the Region of Interest (ROI) of a palm print was crucial for subsequent palm print recognition. However, under unconstrained environmental conditions, the user\'s palm posture and angle, as well as the background and lighting of the environment, were not controlled, making the extraction of the ROI of palm print a major challenge. In existing research methods, traditional ROI extraction methods relied on image segmentation and were difficult to apply to multiple datasets simultaneously under the aforementioned interference. However, deep learning-based methods typically did not consider the computational cost of the model and were difficult to apply to embedded devices. This article proposed a palm print ROI extraction method based on lightweight networks. Firstly, the YOLOv5-lite network was used to detect and preliminarily locate the palm, in order to eliminate most of the interference from complex backgrounds. Then, an improved UNet was used for keypoints detection. This network model reduced the number of parameters compared to the original UNet model, improved network performance, and accelerated network convergence. The output of this model combined Gaussian heatmap regression and direct regression and proposed a joint loss function based on JS loss and L2 loss for supervision. During the experiment, a mixed database consisting of 5 databases was used to meet the needs of practical applications. The results showed that the proposed method achieved an accuracy of 98.3% on the database, with an average detection time of only 28ms on the GPU, which was superior to other mainstream lightweight networks, and the model size was only 831k. In the open-set test, with a success rate of 93.4%, an average detection time of 5.95ms on the GPU, it was far ahead of the latest palm print ROI extraction algorithm and could be applied in practice.
摘要：
准确提取掌纹的感兴趣区域（ROI）对于后续的掌纹识别至关重要。然而,在不受约束的环境条件下，用户的手掌姿势和角度，以及环境的背景和照明，不受控制，使得掌纹的ROI提取成为一个重大挑战。在现有的研究方法中,传统的ROI提取方法依赖于图像分割，在上述干扰下难以同时应用于多个数据集。然而,基于深度学习的方法通常不考虑模型的计算成本，并且难以应用于嵌入式设备。提出了一种基于轻量级网络的掌纹ROI提取方法。首先,YOLOv5-lite网络用于检测和初步定位手掌，以消除大部分来自复杂背景的干扰。然后，改进的UNet用于关键点检测。与原始UNet模型相比，该网络模型减少了参数的数量，改善网络性能，加快网络融合。该模型的输出将高斯热图回归和直接回归相结合，提出了基于JS损失和L2损失的联合损失函数进行监督。在实验过程中,使用由5个数据库组成的混合数据库来满足实际应用的需要。结果表明,该方法在数据库上取得了98.3%的准确率,GPU上的平均检测时间仅为28ms，优于其他主流轻量级网络，模型尺寸仅为831k。在开集测试中，成功率达93.4%,GPU上的平均检测时间为5.95ms，它远远领先于最新的掌纹ROI提取算法，可以在实践中应用。
