基于多角度多区域特征融合的苹果分类方法

doi:10.11772/j.issn.1001-9081.2017102412

计算机应用 ›› 2018, Vol. 38 ›› Issue (5): 1309-1314.DOI: 10.11772/j.issn.1001-9081.2017102412

基于多角度多区域特征融合的苹果分类方法

刘媛媛^1,2,3, 王晖⁴, 郭躬德^1,2,3, 江楠峰^1,2,3

1. 福建师范大学数学与信息学院, 福州 350007;
2. 福建省网络安全与密码技术重点实验室(福建师范大学), 福州 350007;
3. 数字福建环境监测物联网实验室(福建师范大学), 福州 350007;
4. 阿尔斯特大学数学与计算机学院, 英国科尔雷恩 BT52 1SA

收稿日期:2017-10-11 修回日期:2017-11-24 出版日期:2018-05-10 发布日期:2018-05-24
通讯作者: 刘媛媛
作者简介:刘媛媛(1992-),女,河北秦皇岛人,硕士研究生,主要研究方向:数据挖掘、机器学习;王晖(1963-),男,吉林长春人,教授,博士生导师,博士,主要研究方向:数据挖掘、机器学习;郭躬德(1965-),男,福建龙岩人,教授,博士生导师,博士,主要研究方向:统计机器学习、数据挖掘、模式识别;江楠峰(1993-),男,福建龙岩人,硕士研究生,主要研究方向:数据挖掘、机器学习。
基金资助:
国家自然科学基金资助项目（61672157）；福建省科技厅（K类）项目（JK2017007）；福建师范大学网络与信息安全关键理论和技术创新团队项目（IRTL1207）。

Multi-perspective multi-region feature fusion for apple classification

LIU Yuanyuan^1,2,3, WANG Hui⁴, GUO Gongde^1,2,3, JIANG Nanfeng^1,2,3

1. College of Mathematics and Informatics, Fujian Normal University, Fuzhou Fujian 350007, China;
2. Fujian Provincial of Key Laboratory Network Security and Cryptography(Fujian Normal University), Fuzhou Fujian 350007, China;
3. Digit Fujian Internet-of-Things Laboratory of Environmental Monitoring(Fujian Normal Univerisity), Fuzhou Fujian 350007, China;
4. School of Computing and Mathematics, Ulster University at Jordanstown, Coleraine BT52 1SA, UK

Received:2017-10-11 Revised:2017-11-24 Online:2018-05-10 Published:2018-05-24
Contact: 刘媛媛
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61672157), the Fujian Science and Technology Department Project (JK2017007), the Project of Network and Information Security Key Theory and Technological Innovation Team in Fujian Normal University(IRTL1207).

摘要/Abstract

摘要： 日常生活中人们分拣辨别不同种类的苹果需要消耗大量的人力物力，为解决这一问题，提出了一种基于多角度多区域特征融合的苹果图像分类方法。首先，收集五类总共329个苹果，使用手机摄像头从上面、下面和3个不同侧面共五个角度采集每个苹果的图像，每个图像裁剪若干个（1~9）区域块；其次，每个区域块用颜色直方图向量来表示，多个区域块的直方图向量通过首尾相连进行融合，以此生成一个图像的表示；最后，将得到的329个样本数据用12种分类器进行分类比较。实验结果表明，当多角度多区域图像特征融合时，分类效果总是好于单角度单区域，而且越多越好；当使用5个角度的图像，每个图像裁剪9个区域时，偏最小二乘（PLS）分类器的分类精度达到97.87%，好于深度学习。所提方法操作简单、精度较高，算法复杂度为4n，n为图像裁剪区域块总数，可以推广成手机应用，并应用到更多水果和植物图像分类上。

关键词: 图像颜色直方图, 多角度多区域分类, 特征融合, 苹果图像分类, 水果和植物图像分类

Abstract: Since manual sorting of apples is a huge project in our daily life, an apple image classification approach based on multi-perspective multi-region feature fusion was proposed. First of all, five classes of apples, containing 329 in total, were collected. For each apple, five images from five different perspectives were obtained:top, bottom, side1, side2 and side3. From each image, several (one to nine) small image regions were cut. Secondly, each region block was represented by color histogram vector, and the histogram vectors of region blocks were fused together end to end to generate a representation of the image. Finally, 12 classifiers were used to classify 329 samples. The experimental results show that the multi-perspective multi-region based method significantly outperforms single-perspective single-region based method, and the more the number of perspectives/regions, the better the result. In particular, classification performance reaches 97.87% by PLS (Partial Least Squares) even better than deep learning when using nine regions for each image cropped at five angles. The method is easy but efficient, whose computation complexity is 4n, where n is the total number of blocks in image cropping area. Thus, it can be applied to mobile applications and applied to more fruit and plant image classification.

Key words: image color histogram, multi-perspective multi-region classification, feature fusion, apple image classification, fruit and plant image classification

中图分类号:

TP181

刘媛媛, 王晖, 郭躬德, 江楠峰. 基于多角度多区域特征融合的苹果分类方法[J]. 计算机应用, 2018, 38(5): 1309-1314.

LIU Yuanyuan, WANG Hui, GUO Gongde, JIANG Nanfeng. Multi-perspective multi-region feature fusion for apple classification[J]. Journal of Computer Applications, 2018, 38(5): 1309-1314.

参考文献

[1] YUAN L, CAI J, SUN L, et al. A preliminary discrimination of cluster disqualified shape for table grape by nono-camera multi-perspective simultaneously imaging approach[J]. Food Analytical Methods, 2016, 9(3):758-767.
[2] SCHMIDT M A R, BRESSIANI J X, DOS REIS P A, et al. Evaluation of the performance of image classification methods in the identification of vegetation[J]. Journal of Urban & Environmental Engineering, 2016, 10(1):62-71.
[3] WU D, SUN D W. Colour measurements by computer vision for food quality control:a review[J]. Trends in Food Science & Technology, 2013, 29(1):5-20.
[4] LI M, CAO J, LU L. Apple NIR spectral classification method[C]//Proceedings of the 2nd International Conference on Electrical, Computer Engineering and Electronics. Paris:Atlantis Press, 2015:164-167.
[5] BHATT A K, PANT D. Automatic apple grading model development based on back propagation neural network and machine vision, and its performance evaluation[J]. AI & Society, 2015, 30(1):45-56.
[6] CHEN C, WANG Y, ZHOU F. An apple classification algorithm coalescing chromaticity model and fruit radius[J]. Chinese Journal of Quantum Electronics, 2015, 32(2):150-155.
[7] WU X, WU B, SUN J, et al. Classification of apple varieties using near infrared reflectance spectroscopy and fuzzy discriminant c-means clustering model[J]. Journal of Food Process Engineering, 2016, 40(2):1-7.
[8] 卜锡滨, 武斌, 贾红雯. 苹果近红外光谱的特征提取和分类研究[J]. 计算机工程与应用, 2013, 49(2):170-173. (BU X B, WU B, JIA H W. Apple near infrared spectrum feature extraction and classification research[J]. Computer Engineering and Application, 2013, 49(2):170-173.)
[9] SONG W, WANG H, MAGUIRE P, et al. Differentiation of organic and non-organic apples using near infrared reflectance spectroscopy:a pattern recognition approach[C]//Proceedings of the 2016 IEEE SENSORS. Piscataway, NJ:IEEE, 2017:1-3.
[10] KADIR S. Different apple varieties classification using KNN and MLP algorithms[J]. International Journal of Intelligent Systems and Applications in Engineering, 2016, 4(1):166-169.
[11] RONALD M, EVANS M. Classification of selected apple fruit varieties using Naive Bayes[J]. Indian Journal of Computer Science and Engineering, 2016, 7(1):13-19.
[12] SHAHIN M A, TOLLNER E W, ARABNIA H R, et al. Apple classification based on surface bruises using image processing and neural networks[J]. Transactions of the ASAE, 2002, 45(5):1619-1628.
[13] OUYANG W, ZENG X, WANG X, et al. DeepID-Net:deformable deep convolutional neural networks for object detection[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2015:2403-2412.

[1]	王伟, 赵尔平, 崔志远, 孙浩. 基于HowNet义原和Word2vec词向量表示的多特征融合消歧方法[J]. 计算机应用, 2021, 41(8): 2193-2198.
[2]	周险兵, 樊小超, 任鸽, 杨勇. 基于多层次语义特征的英文作文自动评分方法[J]. 计算机应用, 2021, 41(8): 2205-2211.
[3]	吴丽丹, 薛雨阳, 童同, 杜民, 高钦泉. 基于前景语义信息的图像着色算法[J]. 计算机应用, 2021, 41(7): 2048-2053.
[4]	杜炎, 吕良福, 焦一辰. 基于模糊推理的模糊原型网络[J]. 计算机应用, 2021, 41(7): 1885-1890.
[5]	章荪, 尹春勇. 基于多任务学习的时序多模态情感分析模型[J]. 计算机应用, 2021, 41(6): 1631-1639.
[6]	赖雪梅, 唐宏, 陈虹羽, 李珊珊. 基于注意力机制的特征融合-双向门控循环单元多模态情感分析[J]. 计算机应用, 2021, 41(5): 1268-1274.
[7]	卞鹏程, 郑忠龙, 李明禄, 何依然, 王天翔, 张大伟, 陈丽媛. 基于注意力融合网络的视频超分辨率重建[J]. 计算机应用, 2021, 41(4): 1012-1019.
[8]	胡屹杉, 秦品乐, 曾建潮, 柴锐, 王丽芳. 基于特征融合和动态多尺度空洞卷积的超声甲状腺分割网络[J]. 计算机应用, 2021, 41(3): 891-897.
[9]	姜倩玉, 王凤英, 贾立鹏. 基于感知哈希算法和特征融合的恶意代码检测方法[J]. 计算机应用, 2021, 41(3): 780-785.
[10]	后云龙, 朱磊, 陈琴, 吕燧栋. 基于高斯差分特征网络的显著目标检测[J]. 计算机应用, 2021, 41(3): 706-713.
[11]	邱宁佳, 王晓霞, 王鹏, 王艳春. 融合语法规则的双通道中文情感模型分析[J]. 计算机应用, 2021, 41(2): 318-323.
[12]	常峥, 罗萍, 杨波, 张晓晓. 基于HHT-MFCC和短时能量的慢性阻塞性肺病患者呼吸声识别[J]. 计算机应用, 2021, 41(2): 598-603.
[13]	孟祥瑞, 杨文忠, 王婷. 基于图文融合的情感分析研究综述[J]. 计算机应用, 2021, 41(2): 307-317.
[14]	杜培德, 严华. 基于多尺度空间注意力特征融合的人群计数网络[J]. 计算机应用, 2021, 41(2): 537-543.
[15]	刘紫燕, 朱明成, 袁磊, 马珊珊, 陈霖周廷. 基于非局部关注和多重特征融合的视频行人重识别[J]. 计算机应用, 2021, 41(2): 530-536.

基于多角度多区域特征融合的苹果分类方法

Multi-perspective multi-region feature fusion for apple classification

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics