• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.2
• /
• pp.907-923
• /
• 2020

For the severe haze situation in the Beijing-Tianjin-Hebei region, conventional fine particulate matter (PM2.5) concentration prediction methods based on pollutant data face problems such as incomplete data, which may lead to poor prediction performance. Therefore, this paper proposes a method of predicting the PM2.5 concentration based on image analysis technology that combines image data, which can reflect the original weather conditions, with currently popular machine learning methods. First, based on local parameter estimation, autoregressive (AR) model analysis and local estimation of the increase in image blur, we extract features from the weather images using an approach inspired by free energy and a no-reference robust metric model. Next, we compare the coefficient energy and contrast difference of each pixel in the AR model and then use the percentages to calculate the image sharpness to derive the overall mass fraction. Furthermore, the results are compared. The relationship between residual value and PM2.5 concentration is fitted by generalized Gauss distribution (GGD) model. Finally, nonlinear mapping is performed via the wavelet neural network (WNN) method to obtain the PM2.5 concentration. Experimental results obtained on real data show that the proposed method offers an improved prediction accuracy and lower root mean square error (RMSE).

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.3
• /
• pp.1761-1784
• /
• 2017

In order to improve the embedding rate of reversible watermarking algorithm for digital image and enhance the imperceptibility of the watermarked image, an adaptive reversible image watermarking algorithm based on DE is proposed. By analyzing the traditional DE algorithm and the generalized DE algorithm, an improved difference expansion algorithm is proposed. Through the analysis of image texture features, the improved algorithm is used for embedding and extracting the watermark. At the same time, in order to improve the embedding capacity and visual quality, the improved algorithm is optimized in this paper. Simulation results show that the proposed algorithm can not only achieve the blind extraction, but also significantly heighten the embedded capacity and non-perception. Moreover, compared with similar algorithms, it is easy to implement, and the quality of the watermarked images is high.

• Journal of the Semiconductor & Display Technology
• /
• v.18 no.3
• /
• pp.66-71
• /
• 2019

In shape from focus (SFF) methods, the quality of image focus volume plays a vital role in the quality of 3D shape reconstruction. Traditionally, a linear 2D filter is applied to each slice of the image focus volume to rectify the noisy focus measurements. However, this approach is problematic because it also modifies the accurate focus measurements that should ideally remain intact. Therefore, in this paper, we propose to enhance the focus volume adaptively by applying 3-dimensional weighted least squares (3D-WLS) based regularization. We estimate regularization weights from the guidance volume extracted from the image sequences. To solve 3D-WLS optimization problem efficiently, we apply a technique to solve a series of 1D linear sub-problems. Experiments conducted on synthetic and real image sequences demonstrate that the proposed method effectively enhances the image focus volume, ultimately improving the quality of reconstructed shape.

• Journal of Electrical Engineering and Technology
• /
• v.13 no.5
• /
• pp.2099-2106
• /
• 2018

This study presents a novel approach of discriminative feature vectors based on manifold learning using nonlinear dimension reduction (DR) technique to improve loss function, and combine with the Adversarial examples to regularize the object function for image classification. The traditional convolutional neural networks (CNN) with many new regularization approach has been successfully used for image classification tasks, and it achieved good results, hence it costs a lot of Calculated spacing and timing. Significantly, distrinct from traditional CNN, we discriminate the feature vectors for objects without empirically-tuned parameter, these Discriminative features intend to remain the lower-dimensional relationship corresponding high-dimension manifold after projecting the image feature vectors from high-dimension to lower-dimension, and we optimize the constrains of the preserving local features based on manifold, which narrow the mapped feature information from the same class and push different class away. Using Adversarial examples, improved loss function with additional regularization term intends to boost the Robustness and generalization of neural network. experimental results indicate that the approach based on discriminative feature of manifold learning is not only valid, but also more efficient in image classification tasks. Furthermore, the proposed approach achieves competitive classification performances for three benchmark datasets : MNIST, CIFAR-10, SVHN.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 2000.11b
• /
• pp.227-235
• /
• 2000

Agricultural products are easily deformable its shape because of some external forces. However, these force behavior is difficult to measure quantitatively. Until now, many researches on the mechanical property was performed with various methods such as material testing, chemical analysis and non-destructive methods. In order to investigate force behavior on the cellular unit of agricultural products, electro-microscope based 3D image processing method will contribute to analysis of plant cells behavior. Before image measurement of plant cells, plant sample was cut off cross-sectioned area in a size of almost 300-400 ${\mu}$ m units using the micron thickness device, and some of preprocessing procedure was performed with fixing and dyeing. However, the wall structure of plant cell is closely neighbor each other, it is necessary to separate its boundary pixel. Therefore, image merging and shrinking algorithm was adopted to avoid disconnection. After then, boundary pixel was traced through thinning algorithm. Each image from the electro-microscope has a information of x,y position and its height along the z axis cross sectioned image plane. 3D image was constructed using the continuous image combination. Major feature was acquired from a fault image and measured area, thickness of cell wall, shape and unit cell volume. The shape of plant cell was consist of multiple facet shape. Through this measured information, it is possible to construct for structure shape of unit plant cell. This micro unit image processing techniques will contribute to the filed of agricultural mechanical property and will use to construct unit cell model of each agricultural products and information of boundary will use for finite element analysis on unit cell image.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.456-456
• /
• 2000

The back projection histogram method has been proposed as the method to construct an image from waves reflected from a buried object for subsurface radar. This method is compose of two phases, i.e., a back projection image construction process and a back projection image superposition process. A simulation analysis of this method has been studied. In this paper, an experimental study is demonstrated in air as the homogeneous Held using three cylinders as buried objects.

• Proceedings of the Korea Society of Information Technology Applications Conference
• /
• 2005.11a
• /
• pp.173-176
• /
• 2005

This paper proposes a fuzzy correction algorithm that can correct the distorted medical image caused by the scanning nonlinear velocity of the Digital X-ray Scanner System (DX-Scanner) using the Multichannel Ionization Chamber (MIC). In the DX-Scanner, the scanned medical image is distorted for reasons of unsuitable integration time at the nonlinear acceleration period of the AC servo motor during the inspection of patients. The proposed algorithm finds the nonlinear motor velocity modeling through fuzzy system by clustering and reconstructs the normal medical image lines by calculating the suitable moving distance with the velocity of the motor using the modeling, acceleration time and integration time. In addition, several image processing is included in the algorithm. This algorithm analyzes exact pixel lines by comparing the distance of the acceleration period with the distance of the uniform velocity period in every integration time and is able to compensate for the velocity of the acceleration period. By applying the proposed algorithm to the test pattern for checking the image resolution, the effectiveness of this algorithm is verified. The corrected image obtained from distorted image is similar to the normal and better image for a doctor's diagnosis.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.6 no.2
• /
• pp.65-70
• /
• 2013

In this paper, we proposed color image watermarking using human visual system. A watermark is embedded by transforming a color image of RGB coordinate into a color image of HSI coordinate with considering that chromatic components are less sensitive than achromatic components. Watermark is embedded in the frequency domain of the chromatic channels by using discrete cosine transform. Watermark is extracted from watermarked image by using inverse discrete cosine transform. To verify the proposed method, a standard image and a fingerprint image are used for the original image and the watermark image, respectively. Simulation results are satisfied with invisibility and robustness from attacks as image compression.

• Journal of the Semiconductor & Display Technology
• /
• v.14 no.2
• /
• pp.53-59
• /
• 2015

Since the amount of digital image continues to grow in usage, users feel increased difficulty in finding specific images from the image collection. This paper proposes a novel image searching scheme that extracts the image feature using combination of Advanced SURF (Speed-Up Robust Feature) and DCD (Dominant Color Descriptor). The key point of this research is to provide a new feature extraction algorithm to improve the existing SURF method with removal of unnecessary feature in image retrieval, which can be adaptable to mobile system and efficiently run on the mobile environments. To evaluate the proposed scheme, we assessed the performance of simulation in term of average precision and F-score on two databases, commonly used in the field of image retrieval. The experimental results revealed that the proposed algorithm exhibited a significant improvement of over 14.4% in retrieval effectiveness, compared to OpenSURF. The main contribution of this paper is that the proposed approach achieves high accuracy and stability by using ASURF and DCD in searching for natural image on mobile platform.

• Journal of Broadcast Engineering
• /
• v.16 no.2
• /
• pp.319-330
• /
• 2011

For objective assessment of stereoscopic 3D image quality, we measure quality of left and right image with 2D image quality measurement method. However, this method is inconvenient because that we have to measure quality of left and right image individually. Therefore we propose a method of stereoscopic 3D image quality assessment using one overlaid image with left and right image. Using this method, One can measure quality of stereoscopic 3D image more easily and quickly.