Texture-based approach for text detection in images using support vector machines and continuously adaptive mean shift algorithm

For consistency of performance in the shape of the projectile targets, a projectile target detection algorithm is presented based on HOG (Histogram of Oriented Gradient) characterization algorithm. First, detecting the bullet image corner, and secondly, by Mean-shift algorithm improves the corner position accuracy and reduces the number of corner points, finally, applying support vector machines to extract the projectile targets. Compared with the traditional small target detection algorithm, the algorithm describes the targets more accurately, along with better real-time performance. Simulation, the projectile target detection rate of over 80% and verify the effectiveness of the algorithm.

Download Full-text

Texture-Based Text Detection in Digital Images with Wavelet Features and Support Vector Machines

Proceedings of the 8th International Conference on Computer Recognition Systems CORES 2013 - Advances in Intelligent Systems and Computing ◽

10.1007/978-3-319-00969-8_84 ◽

2013 ◽

pp. 857-866 ◽

Cited By ~ 2

Author(s):

Marcin Grzegorzek ◽

Chen Li ◽

Johann Raskatow ◽

Dietrich Paulus ◽

Natalia Vassilieva

Keyword(s):

Support Vector Machines ◽

Digital Images ◽

Text Detection ◽

Support Vector ◽

Vector Machines ◽

Wavelet Features

Download Full-text

An Application of Decision Tree-Based Twin Support Vector Machines to Classify Dephosphorization in BOF Steelmaking

Metals ◽

10.3390/met10010025 ◽

2019 ◽

Vol 10 (1) ◽

pp. 25

Author(s):

Jovan Phull ◽

Juan Egas ◽

Sandip Barui ◽

Sankha Mukherjee ◽

Kinnor Chattopadhyay

Keyword(s):

Support Vector Machines ◽

Decision Tree ◽

Mean Shift ◽

Gaussian Mixture ◽

Partition Ratio ◽

Support Vector ◽

Classification Rate ◽

Twin Support Vector Machines ◽

Slag Chemistry ◽

Vector Machines

Ensuring the high quality of end product steel by removing phosphorus content in Basic Oxygen Furnace (BOF) is essential and otherwise leads to cold shortness. This article aims at understanding the dephosphorization process through end-point P-content in BOF steelmaking based on data-mining techniques. Dephosphorization is often quantified through the partition ratio ( l p ) which is the ratio of wt% P in slag to wt% P in steel. Instead of predicting the values of l p , the present study focuses on the classification of final steel based on slag chemistry and tapping temperature. This classification signifies different degrees (‘High’, ‘Moderate’, ‘Low’, and ‘Very Low’) to which phosphorus is removed in the BOF. Data of slag chemistry and tapping temperature collected from approximately 16,000 heats from two steel plants (Plant I and II) were assigned to four categories based on unsupervised K-means clustering method. An efficient decision tree-based twin support vector machines (TWSVM) algorithm was implemented for category classification. Decision trees were constructed using the concepts: Gaussian mixture model (GMM), mean shift (MS) and affinity propagation (AP) algorithm. The accuracy of the predicted classification was assessed using the classification rate (CR). Model validation was carried out with a five-fold cross validation technique. The fitted model was compared in terms of CR with a decision tree-based support vector machines (SVM) algorithm applied to the same data. The highest accuracy (≥97%) was observed for the GMM-TWSVM model, implying that by manipulating the slag components appropriately using the structure of the model, a greater degree of P-partition can be achieved in BOF.

Download Full-text