Papers by Keyword: Image Classification

Abstract: The paper proposed a deep convolutional neural network together with image processing techniques to detect assembly defects of vehicle components in assembly lines. Traditional detection method such as automatic optical inspection is strongly affected by environmental variation coming from the changes of light source, transfer belt, and component type, therefore, complicated thresholds should be adjusted case by case. The proposed method tries to avoid these problems which is fast and straight forward with satisfactory detection accuracy compared to traditional method.

Abstract: Bacterial Wilt disease is the most determinant factor as it results in a serious reduction in the quality and quantity of food produced by Enset crop. Therefore, early detection of Bacterial Wilt disease is important to diagnose and fight the disease. To this end, a deep learning approach that can detect the disease by using healthy and infected leave images of the crop is proposed. In particular, a convolutional neural network architecture is designed to classify the images collected from different farms as diseased or healthy. A total of 4896 images that were captured directly from the farm with the help of experts in the field of agriculture was used to train the proposed model. The proposed model was trained using these images and data augmentation techniques was applied to generate more images. Besides training the proposed model, a pre-trained model namely VGG16 is trained by using our dataset. The proposed model achieved a mean accuracy of 98.5% and the VGG16 pre-trained model achieved a mean accuracy of 96.6% by using a mini-batch size of 32 and a learning rate of 0.001. The preliminary results demonstrated that the effectiveness of the proposed approach under challenging conditions such as illumination, complex background, different resolutions, variable scale, rotation, and orientation of the real scene images.

Abstract: Image classification is a image processing method which to distinguish between different categories of objectives according to the different features of images. It is widely used in pattern recognition and computer vision. Support Vector Machine (SVM) is a new machine learning method base on statistical learning theory, it has a rigorous mathematical foundation, builts on the structural risk minimization criterion. We design an image classification algorithm based on SVM in this paper, use Gabor wavelet transformation to extract the image feature, use Principal Component Analysis (PCA) to reduce the dimension of feature matrix. We use orange images and LIBSVM software package in our experiments, select RBF as kernel function. The experimetal results demonstrate that the classification accuracy rate of our algorithm beyond 95%.

Abstract: BP algorithm is a classical neural network algorithm. We analyzed the deficiency of traditional BP neural network algorithm, designed new S function and momentum method strategy, optimized the algorithm parameters. We use the new algorithm in the classification of orange images, take color and shape features as input value, the experimental results proved that our algorithm is faster and the classification accuracy rate reaches to 90%

Abstract: This paper proposes a novel multi-view learning framework which leverages the information contained in pseudo-labeled images to improve the prediction performance of image classification using multiple views of an image. In the training process, labeled images are first adopted to train view-specific classifiers independently using uncorrelated and sufficient views, and each view-specific classifier is then iteratively re-trained using initial labeled samples and additional pseudo-labeled samples based on a measure of confidence. In the classification process, the maximum entropy principle is utilized to assign appropriate category label to each unlabeled image using optimally trained view-specific classifiers. Experimental results on a general-purpose image database demonstrate the effectiveness and efficiency of the proposed multi-view semi-supervised scheme.

Abstract: Kernel methods are famous for their efficiency and robustness in processing non-linear machine learning problems in the high dimensional feature space, and thus widely applied in image classification and detection. The proper principal components are selected for KPCA reconstruction according to noise features. Finally, the improved image is obtained by performing inverse method. Experimental results show that the proposed method can suppress noise interference in remote sensing images, and preserve the useful information of original data more completely.

Abstract: This paper proposes a new method for vector quantization by minimizing the Divergence of Kullback-Leibler between the class label distributions over the quantization inputs, which are original vectors, and the output, which is the quantization subsets of the vector set. In this way, the vector quantization output can keep as much information of the class label as possible. An objective function is constructed and we developed an iterative algorithm to minimize it as well. The novel method is evaluated on bag-of-features based image classification problems.

Abstract: A new image classification method based on regions of interest (ROI) and sparse representation is introduced in the paper. Firstly, the saliency map of each image is extracted by different methods. Then, we choose sparse representation to represent and classify the saliency maps. Four different ROI extraction methods are chosen as examples to evaluate the performance of the proposed method. Experimental results show that it is more effective for image classification based on ROI.

Abstract: We use Conditional Random Fields (CRFs) to classify regions in an image. CRFs provide a discriminative framework to incorporate spatial dependencies in an image, which is more appropriate for classification tasks as opposed to a generative framework. In this paper we apply CRFs to the image multi-classification task, we focus on three aspects of the classification task: feature extraction, the Original feature clustering based on K-means, and feature vector modeling base on CRF to obtain multiclass classification. We present classification results on sample images from Cambridge (MSRC) database, and the experimental results show that the method we present can classify the images accurately.

Abstract: Because aluminum profile’s structure is complex and diverse, we need to match the different parameters for different profiles before automated detection of surface defects of aluminum profile. This process often requires manual input, affecting the detection efficiency. To solve this problem, we analyze the characteristics of aluminum profile, through GLCM algorithm and Gabor wavelet transform methods, which are image texture feature extraction methods to get aluminum profile’s texture feature, then we use the Support Vector Machine (SVM) classification algorithm based on radial basis function (RBF) core classify the feature, for the aim of matching parameters automatically. By feature extraction time and the recognition accuracy rate and other indicators to compare the experimental results of each method, derived using Gabor wavelet transform is the best both on recognition accuracy or identify time effects, and can satisfy the actual needs.