Fish image retrieval algorithm based on color four channels and spatial pyramid

doi:10.11772/j.issn.1001-9081.2018112522

Journal of Computer Applications ›› 2019, Vol. 39 ›› Issue (5): 1466-1472.DOI: 10.11772/j.issn.1001-9081.2018112522

• Virtual reality and multimedia computing • Previous Articles Next Articles

Fish image retrieval algorithm based on color four channels and spatial pyramid

ZHANG Meiling^1,2, WU Junfeng^1,2,3, YU Hong¹, CUI Zhen^1,2, DONG Wanting^1,2

1. College of Information Engineering, Dalian Ocean University, Dalian Liaoning 116023, China;
2. Guangdong Province Key Laboratory of Popular High Performance Computers, Shenzhen Guangdong 518060, China;
3. School of Computer Science and Technology, Tianjin University, Tianjin 300072, China

Received:2018-12-04 Revised:2019-02-20 Online:2019-05-14 Published:2019-05-10
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61701070, 61802046), the Natural Science Foundation of Liaoning Province (20170520327), the Project for Institute of Marine Industry Technology of Universities in Liaoning Province (2018-CY-34), the Open fund of Guangdong Province Key Laboratory of Popular High Performance Computers (SZU-GDPHPCL201805), the Technology Program of Dalian (2015A11GX022).

基于颜色四通道及空间金字塔的鱼类图像检索

张美玲^1,2, 吴俊峰^1,2,3, 于红¹, 崔榛^1,2, 董婉婷^1,2

1. 大连海洋大学信息工程学院, 辽宁大连 116023;
2. 广东省普及型高性能计算机重点实验室, 广东深圳 518060;
3. 天津大学计算机科学与技术学院, 天津 30072

通讯作者: 于红
作者简介:张美玲(1992-),女,山西吕梁人,硕士研究生,主要研究方向:计算机视觉、模式识别;吴俊峰(1983-),男,辽宁大连人,讲师,博士,CCF会员,主要研究方向:智能信息处理、计算机视觉;于红(1968-),女,辽宁大连人,教授,博士,CCF会员,主要研究方向:智能信息处理、大数据;崔榛(1995-),女,辽宁丹东人,硕士研究生,主要研究方向:计算机视觉、模式识别;董婉婷(1995-),女,辽宁鞍山人,硕士研究生,主要研究方向:模式识别、大数据。
基金资助:
国家自然科学基金资助项目（61701070，61802046）；辽宁省自然科学基金资助项目（20170520327）；辽宁省高等学校海洋产业技术研究院项目（2018-CY-34）；广东省普及型高性能计算机重点实验室开放基金资助项目（SZU-GDPHPCL201805）；大连市科技计划项目（2015A11GX022）。

Abstract

Abstract: With the development of the application of computer vision in the field of marine fisheries, fish image retrieval has played a huge role in fishery resource survey and fish behavior analysis. It is found that the background information of fish images can greatly interfere with fish image retrieval, and the fish image retrieval results only using color, texture, shape and other characteristics of fish images are not accurate due to the lack of spatial position information. To solve the above problems, a novel fish image retrieval algorithm based on HSVG (Hue, Saturation, Value, Gray) four-channel and spatial pyramid was proposed. Firstly, a visual saliency map was extracted to separate the foreground and the background, thereby reducing the interference of the image background on the retrieval. Then, in order to contain certain spatial position information, the fish image was converted into an HSVG four-channel map, and on this basis, the theory of spatial pyramid was used to segment the image and extract the SURF (Speed Up Robust Feature). Finally, the search results were obtained. In order to verify the effectiveness of the proposed algorithm, the recall and precision of the algorithm were compared with classic HSVG algorithm and saliency block algorithm on QUT_fish_data dataset and DLOU_fish_data dataset. Compared with traditional HSVG algorithm, the precision on two datasets is increased at most by 12% and 5%, and the recall is increased at most by 7% and 22%, respectively. Compared with saliency block algorithm, the precision on two datasets is increased at most by 15% and 5%, and the recall is increased at most by 36% and 22%, respectively. So, the proposed algorithm is effective and can improve the retrieval results significantly.

Key words: fish image retrieval, color channel, spatial pyramid, image feature

摘要： 随着计算机视觉技术在海洋水产领域中的应用不断加深，鱼类图像检索在渔业资源调查、鱼类行为学分析等方面发挥了巨大的作用。通过研究发现，鱼类图像的背景信息会对鱼类图像检索造成极大干扰，而且鱼类图像中颜色、纹理、形状等特征由于空间位置信息的缺乏而使检索的准确率不高。为解决以上问题，提出了一种新的基于颜色四通道及空间金字塔的鱼类图像检索算法。首先，提取视觉显著性图将鱼类图像的前景和背景分开，从而减少图像背景对检索的干扰；其次，为了使图像特征包含一定的空间位置信息，利用空间金字塔的理论对图像进行分割，在此基础上，将图像转为HSVG四通道图并提取SURF特征；；最后，得到检索结果。为验证所提算法的有效性，在QUT_fish_data数据集和DLOU_fish_data数据集上对算法的查全率、查准率与经典的HSVG算法和显著性分块算法进行对比：在两个数据集上查准率分别比传统的HSVG算法最多分别提高12%和5%，查全率最多分别提高7%和22%；比传统的显著性分块算法查准率最多分别提高15%和5%，查全率最多分别提高36%和22%；从而证明所提算法是有效的，能有效提升鱼类图像的检索效果。

关键词: 鱼类图像检索, 颜色通道, 空间金字塔, 图像特征

CLC Number:

TP751

ZHANG Meiling, WU Junfeng, YU Hong, CUI Zhen, DONG Wanting. Fish image retrieval algorithm based on color four channels and spatial pyramid[J]. Journal of Computer Applications, 2019, 39(5): 1466-1472.

张美玲, 吴俊峰, 于红, 崔榛, 董婉婷. 基于颜色四通道及空间金字塔的鱼类图像检索[J]. 计算机应用, 2019, 39(5): 1466-1472.

References

[1] BOSCH A, ZISSERMAN A, MUNOZ X. Scene classification using a hybrid generative/discriminative approach[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 30(4):712-727.
[2] LIAO K, LIU G, HUI Y. An improvement to the SIFT descriptor for image representation and matching[J]. Pattern Recognition Letters, 2013, 34(11):1211-1220.
[3] CHUANG M C, HWANG J N, KUO F F, et al. Recognizing live fish species by hierarchical partial classification based on the exponential benefit[C]// Proceedings of the 2014 IEEE International Conference on Image Processing. Piscataway, NJ: IEEE, 2014:5232-5236.
[4] 黄仁,胡敏.综合颜色空间特征和纹理特征的图像检索[J].计算机科学,2014,41(s1):118-121.(HUANG R, HU M. Content-based image retrieval using color position and texture fused features[J]. Computer Science, 2014, 41(s1):118-121.)
[5] 胡二雷,冯瑞.基于深度学习的图像检索系统[J].计算机系统应用, 2017, 26(3):8-19.(HU E L, FENG R. Image retrieval system based on deep learning[J]. Computer Systems & Applications, 2017, 26(3):8-19.)
[6] GUO T, MOUSAVI H S, MONGA V. Deep learning based image super-resolution with coupled backpropagation[C]// Proceedings of the 2016 IEEE Global Conference on Signal and Information Processing. Piscataway, NJ: IEEE, 2017:237-241.
[7] 张美玲, 吴俊峰, 于红, 等. 一种基于HSVG-SURF特征的鱼类图像检索算法[J]. 小型微型计算机系统, 2018, 39(9): 2085-2089.(ZHANG M L,WU J F,YU H, et al. Fish image retrieval algorithm based on HSVG four channel SURF feature[J]. Journal of Chinese Computer Systems, 2018, 39(9): 2085-2089.)
[8] ZHANG M L, WU J F, Y H, et al. A novel fish image retrieval method based on saliency spatial pyramid[C]// Proceedings of the 201714th International Symposium on Pervasive Systems, Algorithms and Networks & 2017 International Conference on Frontier of Computer Science and Technology & 20173rd International Symposium of Creative Computing. Washington, DC: IEEE Computer Society, 2017: 312-317.
[9] 程少光,何毕,布树辉,等.基于超像素空间金字塔模型的场景识别研究[J].计算机工程与应用,2014, 50(7):139-143.(CHENG S G, HE B, BU S H, et al. Sence recognition research based on SSPM[J]. Computer Engineering and Applications, 2014,50(7):139-143.)
[10] 高常鑫,桑农.整合局部特征和滤波器特征的空间金字塔匹配模型[J]. 电子学报,2011,39(9):2034-2038.(GAO C X, SANG N. Unifying local features and filterbank features in the spatial pyramid matching model[J]. Acta Electronica Sinica,2011,39(9):2034-2038.)
[11] YANG J, YU K, GONG Y, et al. Linear spatial pyramid matching using sparse coding for image classification[C]// Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2009: 1794-1801.
[12] 陈鑫元,李筠,杨海马,等.自适应阈值图像二值化及形态学处理的FPGA实现[J].电子测量技术,2016, 39(7):67-71.(CHEN X Y,LI Y,YANG H M, et al. Adaptive threshold binarization and morphological image processing based on FPGA[J]. Electronic Measurement Technology, 2016, 39(7):67-71.)
[13] WU L S, CHEN J X, WEI L I. Niblack-based binaryzation algorithm for palm vein image[J]. Communications Technology, 2010, 43(1):112-114.
[14] BAY H, TUYTELAARS T, GOOL L V. SURF: Speeded Up Robust Features[C]// Proceedings of the 9th European Conference on Computer Vision. Berlin: Springer, 2006: 404-417.
[15] PYATYKH S, HESSER J, ZHENG L. Image noise level estimation by principal component analysis[J]. IEEE Transactions on Image Processing, 2013, 22(2):687-699.
[16] SALIMI-KHORSHIDI G, SMITH S M, KELTNER J R, et al. Meta-analysis of neuroimaging data: a comparison of image-based and coordinate-based pooling of studies[J]. Neuroimage, 2009, 45(3):10-23.
[17] MURTHY A V, KARAM L J. A MATLAB-based framework for image and video quality evaluation[C]// Proceedings of the 20102nd International Workshop on Quality of Multimedia Experience. Piscataway, NJ: IEEE, 2010:242-247.
[18] SINGHA M, HEMACHANDRAN K. Content based image retrieval using color and texture[J]. Signal & Image Processing, 2012, 3(1):271-273.

Fish image retrieval algorithm based on color four channels and spatial pyramid

基于颜色四通道及空间金字塔的鱼类图像检索

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics

[1]	FENG Xingjie, ZHANG Tianze. Panoptic segmentation algorithm based on grouped convolution for feature fusion [J]. Journal of Computer Applications, 2021, 41(7): 2054-2061.
[2]	CAO Jianfang, TIAN Xiaodong, JIA Yiming, YAN Minmin. Application of improved DeepLabV3+ model in mural segmentation [J]. Journal of Computer Applications, 2021, 41(5): 1471-1476.
[3]	JIANG Qianyu, WANG Fengying, JIA Lipeng. Malware detection method based on perceptual hash algorithm and feature fusion [J]. Journal of Computer Applications, 2021, 41(3): 780-785.
[4]	HU Xueying, GUO Hairu, ZHU Rong. Image super-resolution reconstruction based on hybrid deep convolutional network [J]. Journal of Computer Applications, 2020, 40(7): 2069-2076.
[5]	DENG Tianmin, FANG Fang, ZHOU Zhenhao. Traffic sign recognition based on improved convolutional neural network with spatial pyramid pooling [J]. Journal of Computer Applications, 2020, 40(10): 2872-2880.
[6]	XU Zhe, FENG Changhua. Modified scale dependent pooling model for traffic image recognition [J]. Journal of Computer Applications, 2018, 38(3): 671-676.
[7]	LIU Shengqing, SUN Jifeng, YU Jialin, SONG Zhiguo. Image classification algorithm based on multi-scale feature fusion and Hessian sparse coding [J]. Journal of Computer Applications, 2017, 37(12): 3517-3522.
[8]	LUO Jian, JIANG Min. Object recognition method based on RGB-D image kernel descriptor [J]. Journal of Computer Applications, 2017, 37(1): 255-261.
[9]	CHEN Juanjuan, LIU Caixing, GAO Yuefang, LIANG Yun. Cow recognition algorithm based on improved bag of feature model [J]. Journal of Computer Applications, 2016, 36(8): 2346-2351.
[10]	HAN Fengqing, SONG Zhijian, YU Rui. Fast deduplication for massive images [J]. Journal of Computer Applications, 2016, 36(7): 1797-1800.
[11]	NI Sen, FU Dongmei, DING Ye. Hemorrhagic feature extraction based on different color channels in fundus images [J]. Journal of Computer Applications, 2016, 36(10): 2890-2894.
[12]	YUAN Feiyun. Codebook generation based on self-organizing incremental neural network for image classification [J]. Journal of Computer Applications, 2013, 33(07): 1976-1979.
[13]	HU Yan WANG Huiqin QIN Weiwei ZOU Ting LIANG Junshan. Fire image features selection and recognition based on rough set [J]. Journal of Computer Applications, 2013, 33(03): 704-707.
[14]	KE Dan-dan CAI Guang-cheng CAO Qian-qian. Anisotropic diffusion denoising method based on image feature [J]. Journal of Computer Applications, 2012, 32(03): 742-745.
[15]	HAN Liru. Image features correspondence based on voting of geometric constraint [J]. Journal of Computer Applications, 2011, 31(06): 1595-1597.