• Phonetics and Speech Sciences
• /
• v.3 no.2
• /
• pp.71-78
• /
• 2011

In this paper, we propose an approach which constructs classifier ensembles of various channel compensation and feature enhancement methods. CMN and CMVN are used as channel compensation methods. PCA, kernel PCA, greedy kernel PCA, and kernel multimodal discriminant analysis are used as feature enhancement methods. The proposed ensemble system is constructed with the combination of 15 classifiers which include three channel compensation methods (including 'without compensation') and five feature enhancement methods (including 'without enhancement'). Experimental results show that the proposed ensemble system gives highest average speaker identification rate in various environments (channels, noises, and sessions).

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.4
• /
• pp.980-997
• /
• 2024

To improve the brightness of images and reveal hidden information in dark areas is the main objective of low-light image enhancement (LLIE). LLIE methods based on deep learning show good performance. However, there are some limitations to these methods, such as the complex network model requires highly configurable environments, and deficient enhancement of edge details leads to blurring of the target content. Single-scale feature extraction results in the insufficient recovery of the hidden content of the enhanced images. This paper proposed an edge detection-based multi-scale feature enhancement network for LLIE (EDMFEN). To reduce the loss of edge details in the enhanced images, an edge extraction module consisting of a Sobel operator is introduced to obtain edge information by computing gradients of images. In addition, a multi-scale feature enhancement module (MSFEM) consisting of multi-scale feature extraction block (MSFEB) and a spatial attention mechanism is proposed to thoroughly recover the hidden content of the enhanced images and obtain richer features. Since the fused features may contain some useless information, the MSFEB is introduced so as to obtain the image features with different perceptual fields. To use the multi-scale features more effectively, a spatial attention mechanism module is used to retain the key features and improve the model performance after fusing multi-scale features. Experimental results on two datasets and five baseline datasets show that EDMFEN has good performance when compared with the stateof-the-art LLIE methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.7
• /
• pp.2390-2406
• /
• 2022

Scene text recognition has important application value and attracted the interest of plenty of researchers. At present, many methods have achieved good results, but most of the existing approaches attempt to improve the performance of scene text recognition from the image level. They have a good effect on reading regular scene texts. However, there are still many obstacles to recognizing text on low-quality images such as curved, occlusion, and blur. This exacerbates the difficulty of feature extraction because the image quality is uneven. In addition, the results of model testing are highly dependent on training data, so there is still room for improvement in scene text recognition methods. In this work, we present a natural scene text recognizer to improve the recognition performance from the feature level, which contains feature representation and feature enhancement. In terms of feature representation, we propose an efficient feature extractor combined with Representative Batch Normalization and ResNet. It reduces the dependence of the model on training data and improves the feature representation ability of different instances. In terms of feature enhancement, we use a feature enhancement network to expand the receptive field of feature maps, so that feature maps contain rich feature information. Enhanced feature representation capability helps to improve the recognition performance of the model. We conducted experiments on 7 benchmarks, which shows that this method is highly competitive in recognizing both regular and irregular texts. The method achieved top1 recognition accuracy on four benchmarks of IC03, IC13, IC15, and SVTP.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.2
• /
• pp.544-564
• /
• 2022

Underwater images often suffer from color distortion, blurring and low contrast, which is caused by the propagation of light in the underwater environment being affected by the two processes: absorption and scattering. To cope with the poor quality of underwater images, this paper proposes a multiscale fusion underwater image enhancement method based on channel attention mechanism and local binary pattern (LBP). The network consists of three modules: feature aggregation, image reconstruction and LBP enhancement. The feature aggregation module aggregates feature information at different scales of the image, and the image reconstruction module restores the output features to high-quality underwater images. The network also introduces channel attention mechanism to make the network pay more attention to the channels containing important information. The detail information is protected by real-time superposition with feature information. Experimental results demonstrate that the method in this paper produces results with correct colors and complete details, and outperforms existing methods in quantitative metrics.

• Journal of Information Processing Systems
• /
• v.19 no.3
• /
• pp.370-376
• /
• 2023

Aiming at the problems of low image enhancement accuracy, long enhancement time and poor image quality in the traditional robot sequence motion image enhancement methods, an adaptive enhancement method for robot sequence motion image is proposed. The feature representation of the image was obtained by Karhunen-Loeve (K-L) transformation, and the nonlinear relationship between the robot joint angle and the image feature was established. The trajectory planning was carried out in the robot joint space to generate the robot sequence motion image, and an adaptive homomorphic filter was constructed to process the noise of the robot sequence motion image. According to the noise processing results, the brightness of robot sequence motion image was enhanced by using the multi-scale Retinex algorithm. The simulation results showed that the proposed method had higher accuracy and consumed shorter time for enhancement of robot sequence motion images. The simulation results showed that the image enhancement accuracy of the proposed method could reach 100%. The proposed method has important research significance and economic value in intelligent monitoring, automatic driving, and military fields.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.10
• /
• pp.2367-2374
• /
• 2014

This paper proposes a speech enhancement method which can be independently applied to different types of speech recognition systems. Feature compensation methods are well known to be effective as a front-end algorithm for robust speech recognition in noisy environments. The feature types and speech model employed by the feature compensation methods should be matched with ones of the speech recognition system for their effectiveness. However, they cannot be successfully employed by the speech recognition with "unknown" specification, such as a commercialized speech recognition engine. In this paper, a speech enhancement method is proposed, which is based on the PCGMM-based feature compensation method. The experimental results show that the proposed method significantly outperforms the conventional front-end algorithms for unknown speech recognition over various background noise conditions.

• Journal of Internet Computing and Services
• /
• v.15 no.6
• /
• pp.117-124
• /
• 2014

Cluttered background is a major obstacle in developing salient object detection and tracking system for mobile device captured natural scene video frames. In this paper we propose a context aware feature vector selection model to provide an efficient noise filtering by machine learning based classifiers. Since the context awareness for feature selection is achieved by searching nearest neighborhoods, known as NP hard problem, we apply a fast approximation method with complexity analysis in details. Separability enhancement in feature vector space by adding the context aware feature subsets is studied rigorously using principal component analysis (PCA). Overall performance enhancement is quantified by the statistical measures in terms of the various machine learning models including MLP, SVM, Naïve Bayesian, CART. Summary of computational costs and performance enhancement is also presented.

• The Journal of the Acoustical Society of Korea
• /
• v.38 no.1
• /
• pp.51-55
• /
• 2019

This paper proposes a speech enhancement method utilizing the feature compensation gain for robust speech recognition performances in noisy environments. In this paper we propose a speech enhancement method utilizing the feature compensation gain which is obtained from the PCGMM (Parallel Combined Gaussian Mixture Model)-based feature compensation method employing variational model composition. The experimental results show that the proposed method significantly outperforms the conventional front-end algorithms and our previous research over various background noise types and SNR (Signal to Noise Ratio) conditions in mismatched ASR (Automatic Speech Recognition) system condition. The computation complexity is significantly reduced by employing the noise model selection technique with maintaining the speech recognition performance at a similar level.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.1
• /
• pp.347-370
• /
• 2019

In the computer-aided detection (CAD) system of pulmonary nodules, a high false positive rate is common because the density and the computed tomography (CT) values of the vessel and the nodule in the CT images are similar, which affects the detection accuracy of pulmonary nodules. In this paper, a method of automatic detection of pulmonary nodules based on multi-scale enhancement filters and 3D shape features is proposed. The method uses an iterative threshold and a region growing algorithm to segment lung parenchyma. Two types of multi-scale enhancement filters are constructed to enhance the images of nodules and blood vessels in 3D lung images, and most of the blood vessel images in the nodular images are removed to obtain a suspected nodule image. An 18 neighborhood region growing algorithm is then used to extract the lung nodules. A new pulmonary nodules feature descriptor is proposed, and the features of the suspected nodules are extracted. A support vector machine (SVM) classifier is used to classify the pulmonary nodules. The experimental results show that our method can effectively detect pulmonary nodules and reduce false positive rates, and the feature descriptor proposed in this paper is valid which can be used to distinguish between nodules and blood vessels.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.4
• /
• pp.51-56
• /
• 2018

This paper proposes the efficient preprocessing method based on curvelet transform for edge enhancement in image. The propose method is generated the edge map by using the Canny algorithm to wavelet transform, which is the sub-step of the curvelet transform. In order to improve the part of edge feature, the selective sharpening according to the generate edge map is applied. In experimental result, the propose method achieves that the enhancement of edge feature is better than conventional methods. This leads that peak to signal noise ratio, edge intensity are improvement on average about 1.92, 1.12dB respectively.