Classifying the texture of granules in 2D images has aroused manifold research atten-tion for its technical challenges in image processing areas.This letter presents an aggregate texture identification approach by joi...Classifying the texture of granules in 2D images has aroused manifold research atten-tion for its technical challenges in image processing areas.This letter presents an aggregate texture identification approach by jointly using Gray Level Co-occurrence Probability(GLCP) and BP neural network techniques.First, up to 8 GLCP-associated texture feature parameters are defined and computed, and these consequent parameters next serve as the inputs feeding to the BP neural network to calculate the similarity to any of given aggregate texture type.A finite number of aggregate images of 3 kinds, with each containing specific type of mineral particles, are put to the identification test, experimentally proving the feasibility and robustness of the proposed method.展开更多
The use of computer vision for estimating quality in agriculture products has become wide spread in recent years and the composition,variety,or ripeness can be estimated.On the other hand,the appearance is one of the ...The use of computer vision for estimating quality in agriculture products has become wide spread in recent years and the composition,variety,or ripeness can be estimated.On the other hand,the appearance is one of the most worrying issues for producers due to its influence on quality.In this research,computer vision technology combined with BP artificial neural network(ANN)was developed to identify soybean frogeye,mildewed soybean,worm-eaten soybean and damaged soybean.Thirty-nine characteristic parameters from color,texture and shape characteristics were computed after preprocessing the acquired soybean images.The dimensionality of the characteristic parameters was reduced from 39 dimensionalities to 12 dimensionalities using the method of principal component analysis(PCA).MALAB software was used to build a prediction model according to 12 characteristic parameters.The identification accuracies of soybean frogeye,mildewed soybean,damaged soybean and worm-eaten soybean are 96%,95%,92%,and 92%,respectively.And the accuracy for heterogeneous soybean seeds with several diseases is 90%.The results show that the prediction model constructed by BP neural network can identify the diseases of soybean seeds.And it is useful to estimate appearance quality of soybean by computer vision applying BP neural network.展开更多
岩石薄片的岩性识别是地质分析中不可或缺的一环,其精准度直接影响后续地层岩石种类、性质和矿物成分等信息的确定,对于地质勘探和矿产开采具有重要意义。为了快速准确地识别岩性,本文提出了一种改进的MobileNetV2轻量化模型,通过选取5...岩石薄片的岩性识别是地质分析中不可或缺的一环,其精准度直接影响后续地层岩石种类、性质和矿物成分等信息的确定,对于地质勘探和矿产开采具有重要意义。为了快速准确地识别岩性,本文提出了一种改进的MobileNetV2轻量化模型,通过选取5种岩石类型共3 700张岩石薄片图像进行岩性识别。在MobileNetV2的倒残差结构中嵌入坐标注意力机制,融合图像中多种矿物的全局特征信息。此外,改进MobileNetV2中的分类器,降低模型的参数量和计算复杂度,从而提高模型的运算速度和效率,并采用带泄露线性整流函数(leaky rectified linear unit, Leaky ReLU)作为激活函数,避免网络训练中的梯度消失问题。实验结果表明,本文提出的改进后的MobileNetV2模型大小仅为2.30 MB,在测试集上的精确率、召回率、F_(1)值分别为91.24%、90.18%、90.70%,具有较高的准确性,相比于SqueezeNet、ShuffleNetV2等同类型的轻量化网络,分类效果最好。展开更多
基金Funded by Ningbo Natural Science Foundation (No.2006A610016)
文摘Classifying the texture of granules in 2D images has aroused manifold research atten-tion for its technical challenges in image processing areas.This letter presents an aggregate texture identification approach by jointly using Gray Level Co-occurrence Probability(GLCP) and BP neural network techniques.First, up to 8 GLCP-associated texture feature parameters are defined and computed, and these consequent parameters next serve as the inputs feeding to the BP neural network to calculate the similarity to any of given aggregate texture type.A finite number of aggregate images of 3 kinds, with each containing specific type of mineral particles, are put to the identification test, experimentally proving the feasibility and robustness of the proposed method.
基金We acknowledge the financial support of Heilongjiang Provincial Natural Science Foundation(ZD201303)and Youth Scientific Research Fund of Northeast Agricultural University.
文摘The use of computer vision for estimating quality in agriculture products has become wide spread in recent years and the composition,variety,or ripeness can be estimated.On the other hand,the appearance is one of the most worrying issues for producers due to its influence on quality.In this research,computer vision technology combined with BP artificial neural network(ANN)was developed to identify soybean frogeye,mildewed soybean,worm-eaten soybean and damaged soybean.Thirty-nine characteristic parameters from color,texture and shape characteristics were computed after preprocessing the acquired soybean images.The dimensionality of the characteristic parameters was reduced from 39 dimensionalities to 12 dimensionalities using the method of principal component analysis(PCA).MALAB software was used to build a prediction model according to 12 characteristic parameters.The identification accuracies of soybean frogeye,mildewed soybean,damaged soybean and worm-eaten soybean are 96%,95%,92%,and 92%,respectively.And the accuracy for heterogeneous soybean seeds with several diseases is 90%.The results show that the prediction model constructed by BP neural network can identify the diseases of soybean seeds.And it is useful to estimate appearance quality of soybean by computer vision applying BP neural network.
文摘岩石薄片的岩性识别是地质分析中不可或缺的一环,其精准度直接影响后续地层岩石种类、性质和矿物成分等信息的确定,对于地质勘探和矿产开采具有重要意义。为了快速准确地识别岩性,本文提出了一种改进的MobileNetV2轻量化模型,通过选取5种岩石类型共3 700张岩石薄片图像进行岩性识别。在MobileNetV2的倒残差结构中嵌入坐标注意力机制,融合图像中多种矿物的全局特征信息。此外,改进MobileNetV2中的分类器,降低模型的参数量和计算复杂度,从而提高模型的运算速度和效率,并采用带泄露线性整流函数(leaky rectified linear unit, Leaky ReLU)作为激活函数,避免网络训练中的梯度消失问题。实验结果表明,本文提出的改进后的MobileNetV2模型大小仅为2.30 MB,在测试集上的精确率、召回率、F_(1)值分别为91.24%、90.18%、90.70%,具有较高的准确性,相比于SqueezeNet、ShuffleNetV2等同类型的轻量化网络,分类效果最好。
