为能有效地表示目标轮廓,同时在泛化与鉴别之间做好平衡,将具有生物视觉神经系统的交叉视觉皮层模型神经网络(intersecting cortical model nueral network,ICMNN)与分数幂指数滤波器(fractional power filter,FPF)相结合,设计了一种利...为能有效地表示目标轮廓,同时在泛化与鉴别之间做好平衡,将具有生物视觉神经系统的交叉视觉皮层模型神经网络(intersecting cortical model nueral network,ICMNN)与分数幂指数滤波器(fractional power filter,FPF)相结合,设计了一种利用反馈式ICMNN分离目标轮廓,并使用FPF实现快速相关的剪影识别系统。首先利用ICMNN对原图像处理得到边缘激发的剪影图像,接着利用经训练集合训练好的FPF对ICMNN输出进行相关运算,得到相关面。为了有效减少相似形状带来的误识别错误,将首次检测到的相关峰值点所对应的原图区域通过反馈方式进行增强,再把增强的结果馈入系统,多次迭代后,可有效减少误识别。研究结果表明:该剪影识别系统能较好地应对目标旋转与尺度变化带来的影响,具有较好的应用价值。展开更多
In this article, the local anomalistic blocks such as crypts, furrows, and so on in the iris are initially used directly as iris features. A novel image segmentation method based on intersecting cortical model （ICM）...In this article, the local anomalistic blocks such as crypts, furrows, and so on in the iris are initially used directly as iris features. A novel image segmentation method based on intersecting cortical model （ICM） neural network was introduced to segment these anomalistic blocks. First, the normalized iris image was put into ICM neural network after enhancement. Second, the iris features were segmented out perfectly and were output in binary image type by the ICM neural network. Finally, the fourth output pulse image produced by ICM neural network was chosen as the iris code for the convenience of real time processing. To estimate the performance of the presented method, an iris recognition platform was produced and the Hamming Distance between two iris codes was computed to measure the dissimilarity between them. The experimental results in CASIA v1.0 and Bath iris image databases show that the proposed iris feature extraction algorithm has promising potential in iris recognition.展开更多
文摘为能有效地表示目标轮廓,同时在泛化与鉴别之间做好平衡,将具有生物视觉神经系统的交叉视觉皮层模型神经网络(intersecting cortical model nueral network,ICMNN)与分数幂指数滤波器(fractional power filter,FPF)相结合,设计了一种利用反馈式ICMNN分离目标轮廓,并使用FPF实现快速相关的剪影识别系统。首先利用ICMNN对原图像处理得到边缘激发的剪影图像,接着利用经训练集合训练好的FPF对ICMNN输出进行相关运算,得到相关面。为了有效减少相似形状带来的误识别错误,将首次检测到的相关峰值点所对应的原图区域通过反馈方式进行增强,再把增强的结果馈入系统,多次迭代后,可有效减少误识别。研究结果表明:该剪影识别系统能较好地应对目标旋转与尺度变化带来的影响,具有较好的应用价值。
基金the National Natural Science Foundation of China（6057201）the 985 Special Study Project of Lanzhou University Foundation（LZ985-231-58262-7）
文摘In this article, the local anomalistic blocks such as crypts, furrows, and so on in the iris are initially used directly as iris features. A novel image segmentation method based on intersecting cortical model （ICM） neural network was introduced to segment these anomalistic blocks. First, the normalized iris image was put into ICM neural network after enhancement. Second, the iris features were segmented out perfectly and were output in binary image type by the ICM neural network. Finally, the fourth output pulse image produced by ICM neural network was chosen as the iris code for the convenience of real time processing. To estimate the performance of the presented method, an iris recognition platform was produced and the Hamming Distance between two iris codes was computed to measure the dissimilarity between them. The experimental results in CASIA v1.0 and Bath iris image databases show that the proposed iris feature extraction algorithm has promising potential in iris recognition.
