Deep CNN-based damage classification of milled rice grains using a high-magnification image dataset

Embodiments of the invention disclose an image semantic segmentation method and device, a training method and device, electronic equipment, a storage medium and a program. The image semantic segmentation method comprises the following steps of: carrying out feature extraction on an image to obtain scene features of the image; predicting a semantic category of each pixel in the image according to the scene features so as to obtain an initial semantic segmentation map of the image; predicting object categories in the image according to the scene features and the initial semantic segmentation map, so as to obtain object category response data; and correcting the initial semantic segmentation map according to the object category response data so as to obtain a target semantic segmentation mapof the image. According to the image semantic segmentation method, the image semantic segmentation accuracy can be improved.

Image semantic segmentation method and device, training method and device, electronic equipment, storage medium and program

A method was developed for the determination of the size and size distribution of rice and the amount of broken rice kernels using flatbed scanning (FBS) and image analysis (IA). The rice was placed on the glass plate of the scanner and covered with a black sheet of paper. A fully automatic procedure was developed using freeware IA software and standard spreadsheet software. The method was tested on parboiled and regular-milled white rice of different varieties and compared to manual analysis by weighing after visual separation of whole and broken kernels and by measuring the length and width of rice kernels using a sliding calliper. The FBS method is fast, easy to use and cheap. It yields the same accuracy and better precision than the more time-consuming manual method. Analysis by FBS-IA takes about 3 min per sample compared to about 30 min for manual analysis. The procedure requires a PC with standard desktop scanner.

Determination of the size distribution and percentage of broken kernels of rice using flatbed scanning and image analysis

The images of different flower species had small inter-class variations across different classes as well as large intra-class variations within a class Flower classification techniques are mainly based on the features of color, shape and texture, however, the procedure always involves too many heuristics as well as manual labor to tweak parameters, which often leads to datasets with poor qualitative and quantitative measures The current study proposed a deep architecture of convolutional neural network (CNN) for the purposes of improving the accuracy of identifying the white flowers of Fragaria × ananassa from other three wild flower species of Androsace umbellata (Lour) Merr, Bidens pilosa L and Trifolium repens L in fields The explored CNN architecture consisted of eightfolds of learnable weights including 5 convolutional layers and 3 fully connected layers, which received a true color 227 × 227 pixels flower image as its input The developed CNN detector was able to classify the instances of flowers at overall average accuracies of 992 and 950% in the training and test procedure, respectively The state-of-the-art CNN model was compared with the classical models of the scale-invariant feature transform (SIFT) features and the pyramid histogram of orientated gradient (PHOG) features combined with the multi-class support vector machine (SVM) algorithm The proposed model turned out to be much more accurate than the traditional models of SIFT + SVM at overall average accuracies of 829 and 556% in the training and test procedure and PHOG + SVM at overall average accuracies of 783 and 631%, respectively The proposed state-of-the-art CNN method demonstrates that artificial intelligence is capable of precise classification of the white flower images, whose accuracy is comparable to traditional algorithms The presented algorithm can be further used for the discrimination of white wild flowers in fields

/pdf/deep-convolutional-neural-network-for-automatic-2bjd99v8mp.pdf

Deep convolutional neural network for automatic discrimination between Fragaria × Ananassa flowers and other similar white wild flowers in fields

Artificial intelligence classification of wetland vegetation morphology based on deep convolutional neural network

In this paper, we present a model of a convolutional neural network for automatic extraction of several features of the rice kernels from a gray image The system developed convolutional neural network which is consisted of 7 layers and receives a gray image that measures 200 × 200 pixels as its input Therefore, there are 40000 neurons on the network at the input level The following layer is convolutional with the set of 6 filters Next is the subsampling layer with the maximumvalue function Then, we have one more convolutional layer of 12 filters and the subsampling layer with the maximumvalue function The final is the fully connected layer of 3 neurons The convolutional Neural Networks detector developed were able to identify the grain samples at overall average accuracies of 9952% The study results have demonstrated the capability and potential of machine vision with well-trained convolutional neural network detector for varietal types identification of rice grain samples With the comparably high accuracy of classification obtained, a machine vision together with the developed neural network architectures could be used as a tool to achieve better and more objective rice quality evaluation at trading points within the rice marketing system, and it also provide a superior alternative for other research

Determination of the Varieties of Rice Kernels Based on Machine Vision and Deep Learning Technology

A new method for perceiving origins of international important Ramsar wetland ecological habitat scenes in China

Aiming at solving the problem of real-time monitoring strawberry plant growth in fields, a new scheme based on low-altitude remote sensing technology combined with deep learning is proposed to identify the strawberry plants. The goal is to establish an accurate, fast and reliable strawberry plant counting system, which is a key part to realize the fine management of strawberry planting in fields. To accurately recognize the strawberry plant objects in the complex growing environment, the outer contour characteristics of strawberry plant canopy in the low-altitude remote sensing images in the visible spectrum band is proposed to define the criterion of discriminating the strawberry plants. The state-of-the-art detection framework Faster R-CNN with different deep hierarchical structures is used to train the strawberry plant detection models. The results show that the average precision of the Faster R-CNN with the ResNet-50 backbone reaches 0.9888, which is 2.51% higher than the VGG-16-based model. The presented model can achieve the same accuracy as human beings. In the future, the system is expected to replace the artificial task of identifying the strawberry plants to cut the cost of strawberry production.

Accurate Strawberry Plant Detection System Based on Low-altitude Remote Sensing and Deep Learning Technologies

The invention discloses a method and a device for tracing a multi-modal wetland ecological habitat scene in a nuclear space The device comprises the steps of feature extraction: extracting the global or local features of habitat images in a wetland ecological system by using a space trapping method and a scale invariant feature transformation method; feature preprocessing: conducting normalization processing and centralization processing on the extracted features; feature coupling: projecting heterogeneous features in the nuclear space for coupling by using a kernel principal component analysis method; and tracing: determining the attribution of the wetland ecological habitat scene coupled component features by using a large margin nearest neighbor method The device comprises an imaging device, a mobile flash device, a CF card reader and a PC Compared with a conventional method, the method has the obvious advantages that the heterogeneous-modal wetland ecological habitat feature information is effectively fused in the nuclear space, the attribution of the wetland ecological habitat scene in the nuclear space is determined, the tracing precision is improved, and the method has a good application prospect and a considerable market value

Jianqiang He

Papers

Determination of the Varieties of Rice Kernels Based on Machine Vision and Deep Learning Technology

A new method for perceiving origins of international important Ramsar wetland ecological habitat scenes in China

Accurate Strawberry Plant Detection System Based on Low-altitude Remote Sensing and Deep Learning Technologies

Method and device for tracing multi-modal wetland ecological habitat scene in nuclear space