基于方向梯度直方图和灰度共生矩阵混合特征的金文图像识别

金文图像识别的关键步骤是提取金文的图像特征,针对金文的形态特点,提出了一种基于方向梯度直方图(HOG)和灰度共生矩阵(GLCM)的金文图像识别算法。使用双边滤波对金文图像进行预处理,针对金文的结构特征和局部纹理特征,提取其HOG特征和GLCM特征并将二者进行融合。用融合后的特征作为样本训练支持向量机分类器,用训练后的模型识别金文图像。实验结果表明,该算法相比基于HOG特征的算法,分类准确率提高了19.47个百分点,能更好地提取金文的图像特征,提高识别的准确率。

Abstract

The key step in the process of image recognition of bronze inscriptions is to extract their image features. According to the morphological characteristics of bronze inscriptions, an inscription recognition algorithm based on histogram of oriented gradient (HOG) and gray level co-occurrence matrix (GLCM) is proposed. Using bilateral filtering to preprocess the inscription images, the HOG features and GLCM features are extracted and fused aiming at the structure and local texture features of the bronze inscriptions. The fused features are used as samples to train support vector machine classifier, and the trained model is used to identify the bronze inscription image. Experimental results show that compared with algorithms based on HOG feature, this algorithm improves the classification accuracy by 19.47 percentage points. and can better extract the image features of bronze inscriptions and improve the accuracy of recognition.

参考文献

[1] 吴镇烽. 《商周金文资料通鉴》[EB/OL].( 2005-12-01)[2019-10-20]. http:∥www.cqvip.com/QK/97494X/20085/28325130.html.

Wu Z F. Shangzhou jinwen data general[EB/OL]. ( 2005-12-01)[2019-10-20]. http:∥www.cqvip.com/QK/97494X/20085/28325130.html.

[2] 李昕鑫. 商周金文管理与识别系统的研究与实现[D]. 合肥: 安徽大学, 2014: 12- 29.

Li XX. Research and implementation of management and recognition system of Shang and Zhou dynasties bronze inscription[D]. Hefei: Anhui University, 2014: 12- 29.

[3] , 等. 一种基于深度学习的青铜器铭文识别方法[J]. 自动化学报, 2018, 44(11): 2023-2030.

, et al. A deep learning based method for bronze inscription recognition[J]. Acta Automatica Sinica, 2018, 44(11): 2023-2030.

[4] . 一种新的HOG特征人脸图像识别算法研究[J]. 电子器件, 2019, 42(1): 157-162.

. Research on a new HOG feature face recognition algorithm[J]. Chinese Journal of Electron Devices, 2019, 42(1): 157-162.

[5] . 一种多尺度灰度共生矩阵的纹理特征提取算法[J]. 液晶与显示, 2016, 31(10): 967-972.

. Multi-scale algorithm of texture feature extraction based on gray-level co-occurrence matrix[J]. Chinese Journal of Liquid Crystals and Displays, 2016, 31(10): 967-972.

[6] TomasiC, ManduchiR. Bilateral filtering for gray and color images[C]∥Proceedings of the Sixth International Conference on Computer Vision, January 7, 1998, Bombay, India. New York: IEEE, 1998: 839- 846.

[7] 胡彦新. 基于OMR识别的综合素质评价系统的设计与实现[D]. 长春: 吉林大学, 2017: 20- 30.

Hu YX. Design and implementation of comprehensive quality evaluation system based on OMR[D]. Changchun: Jilin University, 2017: 20- 30.

[8] DalalN, TriggsB. Hlistograms of oriented gradients for human detection[C]∥2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, June 20-25, 2005, San Diego, CA, USA. New York: IEEE, 2005: 886- 893.

[9] 王嘉龙. 基于查询语义相关性分析的图像重排序算法研究[D]. 西安: 西安电子科技大学, 2014: 30- 53.

Wang JL. Image re-ranking based on query depengdent semantic relevance analysis[D]. Xi'an:Xidian University, 2014: 30- 53.

[10] , 等. 基于HOG特征的IKSVM稻瘟病孢子检测[J]. 农业机械学报, 2018, 49(S1): 387-392.

, et al. Spores detection of rice blast by IKSVM based on HOG features[J]. Transactions of the Chinese Society for Agricultural Machinery, 2018, 49(S1): 387-392.

[11] . 基于特征融合与子空间学习的行人重识别算法[J]. 激光与光电子学进展, 2019, 56(2): 021503.

. Person re-identification algorithm based on feature fusion and subspace learning[J]. Laser & Optoelectronics Progress, 2019, 56(2): 021503.

[12] . 信息熵加权的HOG特征提取算法研究[J]. 计算机工程与应用, 2020, 56(6): 147-152.

. Research on HOG feature extraction algorithm weighted by information entropy[J]. Computer Engineering and Applications, 2020, 56(6): 147-152.

[13] . Texture features for image classification[J]. IEEE Transactions on Systems,Man,and Cybernetics, 1973, 3: 610-621.

[14] . 应用改进的灰度共生矩阵识别木材纹理多重特征值[J]. 西北林学院学报, 2019, 34(3): 191-195.

. Application of improved gray symbiosis matrix to identify the multiple characteristic values of wood texture[J]. Journal of Northwest Forestry University, 2019, 34(3): 191-195.

[15] , 等. 古代瓷釉光学相干层析图像的纹理特征分析研究[J]. 中国激光, 2015, 42(5): 0508008.

, et al. Research on texture characteristics analysis of ancient glaze optical coherence tomographic image[J]. Chinese Journal of Lasers, 2015, 42(5): 0508008.

[16] , et al. Random forest and rotation forest for fully polarized SAR image classification using polarimetric and spatial features[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2015, 105: 38-53.

[17] . 基于灰度梯度共生矩阵的桌面灰尘检测算法[J]. 计算机应用, 2019, 39(8): 2414-2419.

. Desktop dust detection algorithm based on gray gradient co-occurrence matrix[J]. Journal of Computer Applications, 2019, 39(8): 2414-2419.

[18] , 等. 一种基于图像特征和神经网络的苹果图像分割算法[J]. 光学学报, 2008, 28(11): 2104-2108.

, et al. Segmentation algorithm for apple recognition using image features and artificial neural network[J]. Acta Optica Sinica, 2008, 28(11): 2104-2108.

赵若晴, 王慧琴, 王可, 王展, 刘文腾. 基于方向梯度直方图和灰度共生矩阵混合特征的金文图像识别[J]. 激光与光电子学进展, 2020, 57(12): 121003. 赵若晴, 王慧琴, 王可, 王展, 刘文腾. Recognition of Bronze Inscriptions Image Based on Mixed Features of Histogram of Oriented Gradient and Gray Level Co-Occurrence Matrix[J]. Laser & Optoelectronics Progress, 2020, 57(12): 121003.

基于方向梯度直方图和灰度共生矩阵混合特征的金文图像识别

关于本站 Cookie 的使用提示

全站搜索

基于方向梯度直方图和灰度共生矩阵混合特征的金文图像识别

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索