Automatic Color Extraction Algorithm of Graphic Design Image Based on Artificial Intelligence

The extraction of color features plays an important role in image recognition and image retrieval. In the past, feature extraction mainly depends on manual or supervised learning, which limits the automation of the whole recognition or retrieval process. In order to solve the above problems, an automatic color extraction algorithm based on artificial intelligence is proposed. According to the characteristics of BMP image, the paper makes use of the conversion between image color space and realizes it in the visual C++6.0 environment. The experimental results show that the algorithm realizes the basic operation of image preprocessing, and realizes the automatic extraction of image color features by proper data clustering algorithm.

Klasifikasi Kualitas Biji Kopi Menggunakan MultilayerPerceptron Berbasis Fitur Warna LCH

Coffee is one of Indonesia's foreign exchange earners and plays an important role in the development of the plantation industry. In previous studies, coffee bean quality research has been carried out using the ANN method using color features. RGB and GLCM. However, the results carried out in the study only had an accuracy value of up to 47%. Therefore, this study aims to improve the performance of coffee bean quality classification using four machine learning methods and 7 color features. From the results obtained, it shows that MultilayerPerceptron is better starting with RGB color with an accuracy of 38% split ratio 90:10. HSV has an accuracy of 57% split ratio 90:10. CMYK has an accuracy of 63% split ratio 90:10. LAB has a 58% curation split ratio of 90:10. The YUV type has an accuracy of 58% split ratio 90:10. Furthermore, the HSI color type has an accuracy of 42% split ratio 90:10. The HCL color type has an accuracy of 65% split ratio 90:10 and LCH has an accuracy of 78% split ratio 90:10. In testing, it can be concluded that the MultilayerPerceptron method is better than other methods for the coffee bean classification process.

Person Re-Identification by Low-Dimensional Features and Metric Learning

Person re-identification (Re-ID) has attracted attention due to its wide range of applications. Most recent studies have focused on the extraction of deep features, while ignoring color features that can remain stable, even for illumination variations and the variation in person pose. There are also few studies that combine the powerful learning capabilities of deep learning with color features. Therefore, we hope to use the advantages of both to design a model with low computational resource consumption and excellent performance to solve the task of person re-identification. In this paper, we designed a color feature containing relative spatial information, namely the color feature with spatial information. Then, bidirectional long short-term memory (BLSTM) networks with an attention mechanism are used to obtain the contextual relationship contained in the hand-crafted color features. Finally, experiments demonstrate that the proposed model can improve the recognition performance compared with traditional methods. At the same time, hand-crafted features based on human prior knowledge not only reduce computational consumption compared with deep learning methods but also make the model more interpretable.

Highlighted Document Image Classification

There are many existing document image classification researches, but most of them are not designed for use in constrained computer resources, like printers, or focused on documents with highlighter pen marks. To enable printers to better discriminate highlighted documents, we designed a set of features in CIE Lch(a* b*) space to use along with the support vector machine. The features include two gamut-based features and six low-level color features. By first identifying the highlight pixels, and then computing the distance from the highlight pixels to the boundary of the printer gamut, the gamut-based features can be obtained. The low-level color features are built upon the color distribution information of the image blocks. The best feature subset of the existing and new features is constructed by sequential forward floating selection (SFFS) feature selection. Leave-one-out cross-validation is performed on a dataset with 400 document images to evaluate the effectiveness of the classification model. The cross-validation results indicate significant improvements over the baseline highlighted document classification model.

Preliminary Study on Sapphire Color Grading Method Based on Automatic Clustering Algorithm of Color Space Features

Traditionally, the color grading of sapphire is mainly based on the naked eye judgment of the appraiser. This judgment standard is not clear enough, and the judgment result has a greater subjective influence, which affects the accuracy of the classification. In this study, the GEM-3000 ultraviolet-visible spectrophotometer was selected, and the color features of 180 sapphire samples were extracted and classified using the CIE1976 color space of the device. The Kmeans algorithm was used to cluster analysis of 140 samples, and the separability of the color space features of different color levels was verified, and the center sample of each color level was obtained. The Euclidean distance between the centers of the remaining 40 samples is calculated, and each color grade prediction label is determined, and the sapphire color is automatically classified based on this. The experimental results show that the accuracy of sapphire color classification using the above method is 97.5%, which confirms the effect and accuracy of the artificial intelligence method in sapphire color classification.

Skin Lesion Classification Based on Surface Fractal Dimensions and Statistical Color Cluster Features Using an Ensemble of Machine Learning Techniques

(1) Background: An approach for skin cancer recognition and classification by implementation of a novel combination of features and two classifiers, as an auxiliary diagnostic method, is proposed. (2) Methods: The predictions are made by k-nearest neighbor with a 5-fold cross validation algorithm and a neural network model to assist dermatologists in the diagnosis of cancerous skin lesions. As a main contribution, this work proposes a descriptor that combines skin surface fractal dimension and relevant color area features for skin lesion classification purposes. The surface fractal dimension is computed using a 2D generalization of Higuchi’s method. A clustering method allows for the selection of the relevant color distribution in skin lesion images by determining the average percentage of color areas within the nevi and melanoma lesion areas. In a classification stage, the Higuchi fractal dimensions (HFDs) and the color features are classified, separately, using a kNN-CV algorithm. In addition, these features are prototypes for a Radial basis function neural network (RBFNN) classifier. The efficiency of our algorithms was verified by utilizing images belonging to the 7-Point, Med-Node, and PH2 databases; (3) Results: Experimental results show that the accuracy of the proposed RBFNN model in skin cancer classification is 95.42% for 7-Point, 94.71% for Med-Node, and 94.88% for PH2, which are all significantly better than that of the kNN algorithm. (4) Conclusions: 2D Higuchi’s surface fractal features have not been previously used for skin lesion classification purpose. We used fractal features further correlated to color features to create a RBFNN classifier that provides high accuracies of classification.

Insulator Contamination Grade Recognition Using the Deep Learning of Color Information of Images

To implement the non-contact detection of contamination on insulators, a contamination severity assessment methodology using the deep learning of the colored image information of insulators can be used. For the insulator images taken at the substation site, a mathematical morphology-improved optimal entropic threshold (OET) method is utilized to extract the insulator from the background. By performing feature calculations of insulator images in RGB and HSI color spaces, sixty-six color features are obtained. By fusing the features of the two color spaces using kernel principal component analysis (KPCA), fused features are obtained. The recognition of contamination grades is then accomplished with a deep belief network (DBN) that consists of a three-layered restricted Boltzmann machine. The experimental results of the images taken on-site show that the fused features obtained by the KPCA can fully reflect the contamination state of the insulators. Compared with the identification obtained using RGB or HSI color-space features alone, accuracy is significantly improved, and insulator contamination grades can be effectively identified. The research provides a new method for the accurate, efficient, and non-contact detection of insulator contamination grades.