Research on Maize Seed Classification Method Based on Convolutional Neural Network

The quality of maize seeds affects the outcome of planting and harvesting,so seed quality inspection has become very important.Traditional seed quality detection methods are labor-intensive and time-consuming,whereas seed quality detection using computer vision techniques is efficient and accurate.In this study,we conducted migration learning training in AlexNet,VGG11 and ShuffleNetV2 network models respectively,and found that ShuffleNetV2 has a high accuracy rate for maize seed classification and recognition by comparing various metrics.In this study,the features of the seed images were extracted through image pre-processing methods,and then the AlexNet,VGG11 and ShuffleNetV2 models were used for training and classification respectively.A total of 2081 seed images containing four varieties were used for training and testing.The experimental results showed that ShuffleNetV2 could efficiently distinguish different varieties of maize seeds with the highest classification accuracy of 100%,where the parameter size of the model was at 20.65 MB and the response time for a single image was at 0.45 s.Therefore,the method is of high practicality and extension value.

Classification of rice seed variety using point cloud data combined with deep learning

Rice variety selection and quality inspection are key links in rice planting.Compared with two-dimensional images,three-dimensional information on rice seeds shows the appearance characteristics of rice seeds more comprehensively and accurately.This study proposed a rice variety classification method using three-dimensional point cloud data of the surface of rice seeds combined with a deep learning network to achieve the rapid and accurate identification of rice varieties.First,a point cloud collection platform was set up with a Raytrix light field camera as the core to collect three-dimensional point cloud data on the surface of rice seeds;then,the collected point cloud was filled,filtered and smoothed;after that,the point cloud segmentation is based on the RANSAC algorithm,and the point cloud downsampling is based on a combination of random sampling algorithm and voxel grid filtering algorithm.Finally,the processed point cloud was input to the improved PointNet network for feature extraction and species classification.The improved PointNet network added a cross-level feature connection structure,made full use of features at different levels,and better extracted the surface structure features of rice seeds.After testing,the improved PointNet model had an average classification accuracy of 89.4%for eight varieties of rice,which was 1.2%higher than that of the PointNet model.The method proposed in this study combined deep learning and point cloud data to achieve the efficient classification of rice varieties.

Classification of pepper seeds using machine vision based on neural network

Pepper is widely planted and used all over the world as fresh vegetable and spice.Genetic and morphological information of pepper are stored through seeds.Determination of seed variety is crucial for correctly identifying genetic materials.Pepper varieties cannot be easily classified even by an expert eye due to the very small size of seeds and visual similarities.Hence,more advanced technologies are required to determine the variety of a pepper seed.A classification method was proposed to discriminate pepper seed based on neural networks and computer vision.Image acquisition was conducted using an office scanner at a resolution of 1200 dpi.Image features representing color,shape,and texture were extracted and used to classify pepper seeds.By calculating features from different color components,a feature database was constructed.Effective features were selected using sequential feature selection with different criterion functions.As a result of the feature selection procedure,the number of the features was significantly reduced from 257 to 10.Cross validation rules were applied to obtain a reliable classification model by preventing overfitting.Different numbers of neurons in the hidden layer and various training algorithms were investigated to determine the best multilayer perceptron model.The best classification performance was obtained using 30 neurons in the hidden layer of the network.With this network,an accuracy rate of 84.94%was achieved using the sequential feature selection and the training algorithm of resilient back propagation in classifying eight pepper seed varieties.

Automatic determination of optimal spectral peaks for classification of Chinese tea varieties using laser-induced breakdown spectroscopy

The accurate identification of tea varieties is of great significance to ensure the interests of tea producers and consumers.As a non-destructive or micro damage detection method,laser-induced breakdown spectroscopy(LIBS)has been widely used in the quality detection or classification of agricultural products and food.The objective of this research was to automatically select optimal spectral peaks from the full LIBS spectra,and develop effective classification model for identifying tea varieties.The LIBS spectra covering the region 200-500 nm were measured for 600 Chinese tea leaves including six varieties(i.e.Longjing green tea,Jinhao black tea,Tie Guanyin,Huang Jinya,White peony tea,and Anhua dark tea).A total of 50 optimal spectral peaks were automatically selected from full LIBS spectra(6102)by using the uninformative variable elimination(UVE)and partial least squares projection analysis,and the selected spectral peaks mainly represent the elemental difference in C,Fe,Mg,Mn,Al and Ca.Partial Least Squares Discriminant Analysis(PLS-DA)was used for developing classification model using selected optimal spectral peaks,and yielded the 99.77%classification accuracy for 300 test samples was reached.The results indicate that the proposed method can be used to identify leaf varieties in various tea products.

Evaluation of grain breakage sensitivity of maize varieties mechanically-harvested by combine harvester

A high grain breakage rate is the main problem that occurs during mechanical maize harvest in China.The breakage sensitivity of different varieties was significantly different,and the breakage resistance is heritable.Therefore,breakage resistant variety screening can help improve the field production efficiency and provide references for breeding work.In this study,42 varieties of maize were harvested with the same mechanical parameters and the same manipulator on a range of harvest dates at experimental stations in Xinxiang,Henan Province,in 2017 and Changji,Xinjiang Province,in 2018 to determine the sensitivity of grain moisture content on grain breakage rate during machine harvest for different varieties.The integral value of the grain breakage rate curve corresponding to the range of 15%to 30%grain moisture content was used as an index that expressed the sensitivity of maize grains to breakage depending on grain moisture content(BSW).Forty-two varieties were categorized as having weak,intermediate,or strong BSW.Among the same four varieties in the two stations,Lianchuang 825 and Lianchuang 808 were classified as sensitive and fragile varieties,Shandan 650 was classified as an intermediate variety,Zeyu 8911 was divided into weak sensitive and breakage-resistance varieties in Xinxiang and intermediate varieties in Changji.The BSW classification results at the two experimental sites were generally consistent,indicating that breakage sensitivity due to moisture content may be a relatively stable genetic characteristic.This study suggested that the integral method for determining BSW can be used to assess the resistance of different maize varieties to grain breakage during mechanical harvesting.The integral method was used to identify twelve breakage-resistant varieties in Xinxiang Station,and six breakage-resistant varieties in Changji Station.This study provides a method for screening maize varieties that are suited to mechanical grain harvesting and for studying the mechanisms of grain breakage resistance.