• Journal of Biosystems Engineering
• /
• v.38 no.3
• /
• pp.192-198
• /
• 2013

Purpose: Methods for non-destructive estimation of product quality have been reported in various industrial fields, but the application of ultrasonic techniques for the agricultural products of potatoes, pears, apples, watermelons, kiwis and tomatoes etc. have been rarely reported since the application of a contact-type ultrasonic transducer in agricultural products is very difficult. Therefore, this study sought to determine the firmness of apples using non-contact ultrasonic techniques. Methods: For this experiment, an ultrasonic experimental tester using a non-contact ultrasonic transducer was created, and a signal processing program was used to analyze the acquired ultrasonic reflected signal. Also, a universal testing machine was used to measure firmness parameters of the apples such as bioyield strength, a firmness factor, after the ultrasonic tests had been performed. Results: Six distance correction factors were calculated to obtain consistent values of ultrasonic properties regardless of the distance between the transducer and the surface of the subject. We developed prediction models of the bioyield strength using the distance correction factors. Conclusions: The optimum prediction model of the bioyield strength of apples using a non-contact ultrasonic technique was a multiple regression model ($R^2=0.9402$).

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2006.06a
• /
• pp.45-48
• /
• 2006

This paper presents an approach to visual information based temporal indexing of video sequences. The objective of this work is the integration of an automatic face detection and a matching system for video indexing. The face detection is done using color information. The matching stage is based on the Principal Component Analysis (PCA) followed by the Minimax Probability Machine (MPM). Using PCA one feature vector is calculated for each face which is detected at the previous stage from the video sequence and MPM is applied to these feature vectors for matching with the training faces which are manually indexed after extracting from video sequences. The integration of the two stages gives good results. The rate of 86.3% correctly classified frames shows the efficiency of our system.

• Journal of the Institute of Convergence Signal Processing
• /
• v.11 no.2
• /
• pp.104-111
• /
• 2010

This paper presents an adaptive image enhancement method using the spatial frequency property in the DCT(discrete cosine transform) compressed domain. The dc coefficients, the illumination components of image, are adjusted to compress the dynamic range of image, and the ac coefficients are modified to enhance the contrast by using the human visual system(HVS) and the spatial frequency property. The ac coefficients are separated into vertical direction, horizontal direction, and mixed spatial frequency components, and adaptively modified to minimize the block artifacts that possibly occur in the image enhancement. The proposed method using dynamic range compression and adaptive contrast enhancement shows the advanced performance without the block artifact compared with existing method.

• Journal of Sasang Constitutional Medicine
• /
• v.17 no.2
• /
• pp.46-51
• /
• 2005

1. Objectives The purpose of this study is to objectify the diagnosis of Sasang Constitution. Using the methods of this study, it will improve to classificate Sasang Constitution. 2. Methods 1) Automatic feature extraction of human frontal faces for Sasang Constitution classification. 2) Color feature extraction of human frontal faces (1)Erosion filtering (skin-white, the other-black) (2) Median median 3. Results and Conclusions Observing a person's shape has been the major method for Sasang Constitution classification, which usually has been dependent upon doctor's intuition as of these days. We are developing an automatic system which provides objective basic data for Sasang Constitution classification. For this, in this paper, firstly, the signal processing techniques are applied to automatic feature extraction of human frontal faces for Sasang Constitution classification. The experiment is conducted to verify the effectiveness of the proposed system.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.05a
• /
• pp.666-668
• /
• 2016

Salt and pepper noise generally occurs due to errors in the transmission channel or sensors and it lowers the resolution of the image and causes visual errors. To remove this salt and pepper noise, SMF(standard median filter), which represents simple algorithm and excellent noise removal performance, is widely used. However preservation characteristics in the pitch areas of the image is rather lacking. Therefore to effectively restore images damaged by salt and pepper noise, the study suggested a multiple filter that applies filters differently according to size by applying noise density threshold value of local mask on noise signal, while preserving non-noise signal.

• Investigative Magnetic Resonance Imaging
• /
• v.19 no.2
• /
• pp.117-121
• /
• 2015

Chordoid glioma is a rare, low-grade brain neoplasm typically located in the third ventricle. Herein, we report an unusual case of histologically confirmed chordoid glioma located in the pituitary fossa and suprasellar region, not attached to the third ventricle. A 57-year-old woman presented with a 2-month history of headache and visual disturbance. Magnetic resonance imaging revealed an ovoid mass in the pituitary fossa and suprasellar region, compressing the optic chiasm without involvement of the third ventricle. The tumor showed low signal intensity on T1-weighted images and iso- to high signal intensity on T2-weighted images, with strong and homogenous contrast enhancement. Subtotal resection was performed via the transcranial approach, and the patient subsequently received adjuvant gamma knife radiosurgery. However, the residual mass showed disease progression 5 months after the initial surgery.

• Journal of the Institute of Convergence Signal Processing
• /
• v.5 no.2
• /
• pp.91-95
• /
• 2004

In this paper, we propose a fuzzy controller for the evaluation of the quantization parameters in the H.263 coder. Our method adopts the Mamdani method for fuzzification and adopts the centroid method for defuzzification respectively. The inputs are variance, entropy in the spatial domain, current motion vector and previous motion vector in the temporal. Fuzzy variables are determined to be compatible in visual characteristics and fuzzy membership function is induced and then, FAM banks are designed to reduce the number of rules. In this paper, fuzzy quantization has been applied to a practical video compression. This results show that the quality of decode image enhances and the rate control method using fuzzy quantization is effective.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.4
• /
• pp.522-527
• /
• 2010

In this paper, a new MBHF(Morphology-Based Homomorphic filter) is presented to enhance contrast in mammographic images. The MBH filtering is performed based on the morphological sub-bands, in which an image is morphologically decomposed. The filter is designed to have optimal gain and structuring element in each sub-band through differential evolution. Experimental results show that the proposed method improves the contrast in mammographic images such that an evaluation criterion, WPSNR(Weighted Peak Signal to Noise Ratio) which takes into account human visual system is increased compared with a wavelet-based Homomorphic filter.

• Journal of Information Processing Systems
• /
• v.17 no.4
• /
• pp.754-771
• /
• 2021

In the task of continuous dimension emotion recognition, the parts that highlight the emotional expression are not the same in each mode, and the influences of different modes on the emotional state is also different. Therefore, this paper studies the fusion of the two most important modes in emotional recognition (voice and visual expression), and proposes a two-mode dual-modal emotion recognition method combined with the attention mechanism of the improved AlexNet network. After a simple preprocessing of the audio signal and the video signal, respectively, the first step is to use the prior knowledge to realize the extraction of audio characteristics. Then, facial expression features are extracted by the improved AlexNet network. Finally, the multimodal attention mechanism is used to fuse facial expression features and audio features, and the improved loss function is used to optimize the modal missing problem, so as to improve the robustness of the model and the performance of emotion recognition. The experimental results show that the concordance coefficient of the proposed model in the two dimensions of arousal and valence (concordance correlation coefficient) were 0.729 and 0.718, respectively, which are superior to several comparative algorithms.

• Journal of Biomedical Engineering Research
• /
• v.38 no.1
• /
• pp.16-24
• /
• 2017

For the development of feasible retinal prosthesis, one of the important elements is acquiring proper judging tool if electrical stimulus leads to patient's visual perception. If evoked potential to electrical stimulus is recorded in primary visual (V1) cortex, it means that the stimulus effectively evokes visual perception. Therefore, in this study, we established VEP recording system on V1 cortex using BioPAC modules as the judging tool. And the measuring system was evaluated by recording VEP of mice. After anesthesia, normal mice (C57BL/6J strain; n = 6) were secured to stereotaxic apparatus (Harvard Apparatus, USA). For the recording of VEP, the stainless steel needle electrode (impedance: $2-5k{\Omega}$) was positioned on the surface of the cortex through the burr hole at 2.5 mm lateral and 4.6 mm caudal to bregma. DA 100C and EEG 100C BioPAC modules were used for the trigger signal and VEP recording, respectively. When left eye was blocked by black cover and right eye was stimulated by flash light using HMsERG (RetVet Corp, USA), VEP response at left V1 cortex was detected, but there was no response at right V1 cortex. Amplitudes and latencies of P2, N3 peaks of VEP recording varied according to the depths of the electrodes on V1 cortex. From the surface upto $600{\mu}m$ depth, amplitudes of P2 and N3 increased, while deeper than $600{\mu}m$, those amplitudes decreased. The deeper the insertion depth of the electrode, the latency of N1 peaks tends to be delayed. However, there was no statistically significant difference among the latencies of P2 and N3 peaks (P > 0.05, ANOVA). Our VEP recording data such as the insertion depth and the latency and amplitudes of peaks might be used as guidelines for electrically-evoked potential (EEP) recording experiment in near future.