The artificial intelligence method, combined with feature extraction algorithm, is proposed in this paper to improve the accuracy and efficiency of handwritten character recognition. This paper presents a novel featur...
详细信息
The artificial intelligence method, combined with feature extraction algorithm, is proposed in this paper to improve the accuracy and efficiency of handwritten character recognition. This paper presents a novel featureextraction method by a neural response, which is introduced by merging the hierarchical architectures with the sparse coding approach. Regarding the proposed layered model, sparse coding and pooling operations are utilized in each layer of the hierarchy. This paper also presents a new method that employs the formulated hierarchical sparse method to increase the recognition rate of offline handwritten characters. Experimental results demonstrate that the proposed method can rapidly and accurately perform the required task.
We demonstrated the multimodal optical excitation pulsed thermography, and this technique can enhance the defect detectability and the depth-resolution dynamic range for the propellant /cladding layer interface debond...
详细信息
We demonstrated the multimodal optical excitation pulsed thermography, and this technique can enhance the defect detectability and the depth-resolution dynamic range for the propellant /cladding layer interface debonding defects of the solid propellant rocket motor. Firstly, threedimensional (3D) thermal-wave model which stimulated by a pulse excitation thermal source was built. The temperature field distribution and the thermal-wave diffusion behavior were analyzed. Subsequently, multiple feature extraction algorithms were proposed and applied to extract characteristic images. The experimental set-up was developed and utilized to detect cladding layers with artificial defects. The results demonstrate that pulse thermography optimized by PLSR and ICA can achieve better detection of interface debonding defects. The characteristic profiles were analyzed to evaluate the ability of feature images to characterize the defect diameter and depth. The results depict that the 1st independent component has a better detection effect for defect depth and diameter.
Moisture content detection has guiding significance for the storage and quality detection of rice. To detect moisture content rapidly and non-destructively, hyperspectral imaging technology (400-1000 nm) was employed ...
详细信息
Moisture content detection has guiding significance for the storage and quality detection of rice. To detect moisture content rapidly and non-destructively, hyperspectral imaging technology (400-1000 nm) was employed to analyze rice with different moisture content, and Savitzky-Golay mixed standard normalized variable algorithm (SG-SNV) was used for spectral data pretreatment. Furthermore, a modified supervised locality preserving projections (MSLPP) method was proposed to extract spectral features. The modeling results showed that MSLPP had better spectral featureextraction performance. Finally, to improve prediction accuracy, the equilibrium slime mold algorithm (ESMA) was introduced to obtain the optimal parameters (c, g) of the support vector regression (SVR) model. And MSLPP-ESMA-SVR model had higher prediction accuracy and stronger robustness, with R-p(2) reaching 0.9755 and root mean square error of prediction reaching 0.8597%. Therefore, hyperspectral imaging technology combined with MSLPP-ESMA-SVR model is feasible to detect rice moisture content.
Printed circuit board (PCB) layout is becoming high density, high performance, light, and short. In the automatic PCB defect detection system, image registration of PCB plays an important role. However, most of the tr...
详细信息
Printed circuit board (PCB) layout is becoming high density, high performance, light, and short. In the automatic PCB defect detection system, image registration of PCB plays an important role. However, most of the traditional registration methods are inefficient, and cannot cope with the problems of image distortion, affine, noise, and so on. To address this issue, the authors propose an improved scale invariant feature transform (SIFT) feature extraction algorithm combined with particle swarm optimisation (PSO) to register the images of PCB which placed on a conveyor belt. The advantage of the presented approach is that the registration results are more robust and efficient by optimising the existing PCB image matching framework. The experimental results on the proposed PCB datasets show that the speed of the proposed method (improved SIFT-PSO) is faster than the traditional SIFT feature registration method, and the average computing time of processing single picture can be improved by 10 s, the registration accuracy can be improved by 3-4%. Compared with the experimental results of other algorithms, the root-mean-square error can be reduced to 0.5146 by using the proposed method. Thus, the proposed method (improved SIFT-PSO) is more accurate and robust in real-time inspection system of PCB.
暂无评论