Pub Date : 2017-11-01DOI: 10.1109/ICAWST.2017.8256447
K. Chiou, Hsiu-Hui Su, Yu-Ying Hsieh, Chung-Han Tien
Nowadays people become more aware of good nutrition due to food scandals. The main products are nutritional supplements which are selling by distributors in Taiwan. This study aims to evaluate whether members loyalty is increased. The study conducts survey according to the members of company S as the participants. For the sake of evaluating service quality of company S and member loyalty, Importance-performance Analysis (IPA) identifies two improvements in need of improvement from 18 questions of the questionnaire and to provide strategies. Moreover, simultaneous importance-performance analysis listed improvement to evaluate the improvement of assessment to enhance member loyalty and company's business performance.
{"title":"Application of simultaneous importance-performance analysis to evaluate customer loyalty towards corporation: A case study of direct selling company S","authors":"K. Chiou, Hsiu-Hui Su, Yu-Ying Hsieh, Chung-Han Tien","doi":"10.1109/ICAWST.2017.8256447","DOIUrl":"https://doi.org/10.1109/ICAWST.2017.8256447","url":null,"abstract":"Nowadays people become more aware of good nutrition due to food scandals. The main products are nutritional supplements which are selling by distributors in Taiwan. This study aims to evaluate whether members loyalty is increased. The study conducts survey according to the members of company S as the participants. For the sake of evaluating service quality of company S and member loyalty, Importance-performance Analysis (IPA) identifies two improvements in need of improvement from 18 questions of the questionnaire and to provide strategies. Moreover, simultaneous importance-performance analysis listed improvement to evaluate the improvement of assessment to enhance member loyalty and company's business performance.","PeriodicalId":378618,"journal":{"name":"2017 IEEE 8th International Conference on Awareness Science and Technology (iCAST)","volume":"196 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134381578","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-11-01DOI: 10.1109/ICAWST.2017.8256493
Tsung-Hsin Wei, Ju-Chin Chen
In this paper, we proposed a video super-resolution (SR) system. Image or video super-resolution has been studied for a long time. Recently, convolutional neural network (CNN) has been applied for image SR and provided impressive synthesized high-resolution results. Although CNN can provide better synthesized quality than traditional SR methods by preserving more high frequency information, the computational complexity is main concern for video super-resolution. In order to accelerate processing time, we integrated motion information into the SR system and then the SRCNN is used to reconstruct high resolution image. In other words, rather than reconstructing the whole frames for the input video, changed regions between two consecutive frames are explored and processed. Only unmatched patches were reconstructed via SRCNN in the proposed system. In addition, two additional strategies are proposed to speed up the processing time and reduce unexpected synthesized effects. According experimental results, the proposed system can save 37% computation time in one test video with dynamic changes.
{"title":"Integrating motion estimation and convolutional neural network for video super-resolution","authors":"Tsung-Hsin Wei, Ju-Chin Chen","doi":"10.1109/ICAWST.2017.8256493","DOIUrl":"https://doi.org/10.1109/ICAWST.2017.8256493","url":null,"abstract":"In this paper, we proposed a video super-resolution (SR) system. Image or video super-resolution has been studied for a long time. Recently, convolutional neural network (CNN) has been applied for image SR and provided impressive synthesized high-resolution results. Although CNN can provide better synthesized quality than traditional SR methods by preserving more high frequency information, the computational complexity is main concern for video super-resolution. In order to accelerate processing time, we integrated motion information into the SR system and then the SRCNN is used to reconstruct high resolution image. In other words, rather than reconstructing the whole frames for the input video, changed regions between two consecutive frames are explored and processed. Only unmatched patches were reconstructed via SRCNN in the proposed system. In addition, two additional strategies are proposed to speed up the processing time and reduce unexpected synthesized effects. According experimental results, the proposed system can save 37% computation time in one test video with dynamic changes.","PeriodicalId":378618,"journal":{"name":"2017 IEEE 8th International Conference on Awareness Science and Technology (iCAST)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127979979","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-11-01DOI: 10.1109/ICAWST.2017.8256519
K. Huang, Shann-Bin Chang, Lieh-Dai Yang
A cluster validity index (CVI) classification method is applied to enhance the performance of existing Multiple-Attribute Decision Making (MADM) method. This paper proposed index-based method is called the FRM-index method which combined Fuzzy Set (FS), Rough Set (RS), and a cluster validity index function. The effectiveness of the proposed FRM-index method is evaluated by comparing the classification results obtained for the relating UCI datasets using a statistical approach. Overall, the results show that the proposed method not only provides a more reliable basis for the extraction of decisionmaking rules for multi-output datasets, but also fills out the uncertainty and facilitates an effective MADM built.
{"title":"The approach to classifying multi-output datasets based on cluster validity index method","authors":"K. Huang, Shann-Bin Chang, Lieh-Dai Yang","doi":"10.1109/ICAWST.2017.8256519","DOIUrl":"https://doi.org/10.1109/ICAWST.2017.8256519","url":null,"abstract":"A cluster validity index (CVI) classification method is applied to enhance the performance of existing Multiple-Attribute Decision Making (MADM) method. This paper proposed index-based method is called the FRM-index method which combined Fuzzy Set (FS), Rough Set (RS), and a cluster validity index function. The effectiveness of the proposed FRM-index method is evaluated by comparing the classification results obtained for the relating UCI datasets using a statistical approach. Overall, the results show that the proposed method not only provides a more reliable basis for the extraction of decisionmaking rules for multi-output datasets, but also fills out the uncertainty and facilitates an effective MADM built.","PeriodicalId":378618,"journal":{"name":"2017 IEEE 8th International Conference on Awareness Science and Technology (iCAST)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116119240","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-11-01DOI: 10.1109/ICAWST.2017.8256507
Pengfei Song, Jeng-Shyang Pan, Chun-Sheng Yang, Chiou-Yng Lee
Number theoretic transform with the modular arithmetic operations can perform convolution efficiently in a ring without round-off errors. In this paper, a new efficient architecture of the transform have been proposed which support a various operand size. To have a balanced trade-off between area and latency, a variant constant geometry architecture is used which the forward and backward sub-stage used the same computation pattern. In addition, a XOR-based multi-ported RAM is adopted to accelerate the memory access which allow multiple simultaneous reads and writes efficiently. As a result, the developed accelerator can achieve lower area-latency FPGA compared to other designs.
{"title":"An efficient FPGA-based accelerator design for convolution","authors":"Pengfei Song, Jeng-Shyang Pan, Chun-Sheng Yang, Chiou-Yng Lee","doi":"10.1109/ICAWST.2017.8256507","DOIUrl":"https://doi.org/10.1109/ICAWST.2017.8256507","url":null,"abstract":"Number theoretic transform with the modular arithmetic operations can perform convolution efficiently in a ring without round-off errors. In this paper, a new efficient architecture of the transform have been proposed which support a various operand size. To have a balanced trade-off between area and latency, a variant constant geometry architecture is used which the forward and backward sub-stage used the same computation pattern. In addition, a XOR-based multi-ported RAM is adopted to accelerate the memory access which allow multiple simultaneous reads and writes efficiently. As a result, the developed accelerator can achieve lower area-latency FPGA compared to other designs.","PeriodicalId":378618,"journal":{"name":"2017 IEEE 8th International Conference on Awareness Science and Technology (iCAST)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121704278","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-11-01DOI: 10.1109/ICAWST.2017.8256465
M. Chiang, Hui-Ching Hsieh, Weng-Chung Tsai, Ming-Ching Ke
In recent decades, with the rapid development and popularization of Internet and computer technology, cloud computing had become a highly-demanded service due to the advantages of high computing power, cheap cost of services, scalability, accessibility as well as availability. However, a fly in the ointment was that the system is more complex while dispatching variety of tasks to servers. It means that dispatching tasks to the servers is a challenge since there has a large number of heterogeneous servers, core and diverse application services need to cooperate with each other in the cloud computing network. To deal with the huge number of tasks, an appropriate and effective scheduling algorithm is to allocate these tasks to appropriate servers within the minimum completion time, and to achieve the load balancing of workload. Based on the reasons above, a novel dispatching algorithm, called Advanced MaxSufferage algorithm (AMS), is proposed in this paper to improve the dispatching efficiency in the cloud computing network. The main concept of the AMS is to allocate the tasks to server nodes by comparing the SV value, MSV value, and average value of expected completion time of the server nodes between each task. Basically, the AMS algorithm can obtain better task completion time than previous works and can achieve loadbalancing in cloud computing network.
{"title":"An improved task scheduling and load balancing algorithm under the heterogeneous cloud computing network","authors":"M. Chiang, Hui-Ching Hsieh, Weng-Chung Tsai, Ming-Ching Ke","doi":"10.1109/ICAWST.2017.8256465","DOIUrl":"https://doi.org/10.1109/ICAWST.2017.8256465","url":null,"abstract":"In recent decades, with the rapid development and popularization of Internet and computer technology, cloud computing had become a highly-demanded service due to the advantages of high computing power, cheap cost of services, scalability, accessibility as well as availability. However, a fly in the ointment was that the system is more complex while dispatching variety of tasks to servers. It means that dispatching tasks to the servers is a challenge since there has a large number of heterogeneous servers, core and diverse application services need to cooperate with each other in the cloud computing network. To deal with the huge number of tasks, an appropriate and effective scheduling algorithm is to allocate these tasks to appropriate servers within the minimum completion time, and to achieve the load balancing of workload. Based on the reasons above, a novel dispatching algorithm, called Advanced MaxSufferage algorithm (AMS), is proposed in this paper to improve the dispatching efficiency in the cloud computing network. The main concept of the AMS is to allocate the tasks to server nodes by comparing the SV value, MSV value, and average value of expected completion time of the server nodes between each task. Basically, the AMS algorithm can obtain better task completion time than previous works and can achieve loadbalancing in cloud computing network.","PeriodicalId":378618,"journal":{"name":"2017 IEEE 8th International Conference on Awareness Science and Technology (iCAST)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128107950","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-11-01DOI: 10.1109/ICAWST.2017.8256448
Hsinying Liang, Kuan-Chung Chou, Hung-Chi Chu
This paper proposes a modified selective mapping (SLM) technique to improve the high computational complexity required for the SLM technique in the orthogonal frequency division multiplexing (OFDM) system, and it can be regarded as a suboptimal SLM technique for peak to average power ratio (PAPR) reduction. The proposed method which generates W candidate signals is through the phase factor to carry out the first phase scrambling for the input signal to produce W/2 signals, followed by the inverse fast Fourier transform (IFFT) and then the second phase scrambling to produce the remaining W/2 signals. The generation mechanism of the phase factor is mainly based on the sub-code of the Reed-Muller codes with random ordering. The simulation results show that adopting the proposed method results in the improved performance of PAPR that are suboptimal compared to adopting the SLM technique but it simplifies the number of adders and multipliers required by the traditional SLM technique.
{"title":"A modified SLM scheme with two-stage scrambling for PAPR reduction in OFDM systems","authors":"Hsinying Liang, Kuan-Chung Chou, Hung-Chi Chu","doi":"10.1109/ICAWST.2017.8256448","DOIUrl":"https://doi.org/10.1109/ICAWST.2017.8256448","url":null,"abstract":"This paper proposes a modified selective mapping (SLM) technique to improve the high computational complexity required for the SLM technique in the orthogonal frequency division multiplexing (OFDM) system, and it can be regarded as a suboptimal SLM technique for peak to average power ratio (PAPR) reduction. The proposed method which generates W candidate signals is through the phase factor to carry out the first phase scrambling for the input signal to produce W/2 signals, followed by the inverse fast Fourier transform (IFFT) and then the second phase scrambling to produce the remaining W/2 signals. The generation mechanism of the phase factor is mainly based on the sub-code of the Reed-Muller codes with random ordering. The simulation results show that adopting the proposed method results in the improved performance of PAPR that are suboptimal compared to adopting the SLM technique but it simplifies the number of adders and multipliers required by the traditional SLM technique.","PeriodicalId":378618,"journal":{"name":"2017 IEEE 8th International Conference on Awareness Science and Technology (iCAST)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133640240","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-11-01DOI: 10.1109/ICAWST.2017.8256470
Li-Hua Li, F. Lee, Bo-Liang Chen, Shin-Fu Chen
As the development and population of Electronic Commerce (EC) keeps growing, the sheer volume of data makes the EC more challenge to handle. For example, if the number of products keeps increasing, a regular user-item transaction records may get bigger and bigger which will usually form the sparse matrix. When the data sparsity is formed, the performance of data analysis should be aware. In order to promote the product under hundreds or thousands of items, recommender systems have been intensively studied and are highly applied in the EC environment. One of the most popular recommendation methods is the collaborative filtering (CF) method in which a group of user/customer with similar preference is chosen for the reference of recommendation. It is interesting to notice that the past researches usually didn't consider the sparsity problem when applying the CF recommendation. As a result, the time performance of CF recommendation is, therefore, constrained. To overcome this problem, this research proposes a Simplified Similarity Measure (SSM) for CF recommendation when dealing with the sparsity problem. The proposed SSM method uses the real data from Epinion.com for experiment and for comparison. The results show that SSM method is outperformed the traditional CF methods in terms of time efficiency and recommendation precision.
{"title":"A simplified method for improving the performance of product recommendation with sparse data","authors":"Li-Hua Li, F. Lee, Bo-Liang Chen, Shin-Fu Chen","doi":"10.1109/ICAWST.2017.8256470","DOIUrl":"https://doi.org/10.1109/ICAWST.2017.8256470","url":null,"abstract":"As the development and population of Electronic Commerce (EC) keeps growing, the sheer volume of data makes the EC more challenge to handle. For example, if the number of products keeps increasing, a regular user-item transaction records may get bigger and bigger which will usually form the sparse matrix. When the data sparsity is formed, the performance of data analysis should be aware. In order to promote the product under hundreds or thousands of items, recommender systems have been intensively studied and are highly applied in the EC environment. One of the most popular recommendation methods is the collaborative filtering (CF) method in which a group of user/customer with similar preference is chosen for the reference of recommendation. It is interesting to notice that the past researches usually didn't consider the sparsity problem when applying the CF recommendation. As a result, the time performance of CF recommendation is, therefore, constrained. To overcome this problem, this research proposes a Simplified Similarity Measure (SSM) for CF recommendation when dealing with the sparsity problem. The proposed SSM method uses the real data from Epinion.com for experiment and for comparison. The results show that SSM method is outperformed the traditional CF methods in terms of time efficiency and recommendation precision.","PeriodicalId":378618,"journal":{"name":"2017 IEEE 8th International Conference on Awareness Science and Technology (iCAST)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130109197","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-11-01DOI: 10.1109/ICAWST.2017.8256503
Yu-Yan Chen, Jiun-Jian Liaw
The Illegal logging (IL) has become an extremely important issue. We are trying to deploy the sensors in the forest. The sensors will send the data of illegal logging event while it happened. This paper is aiming to recognize the vibration of illegal logging events and the technique of illegal logging sound recognition. Two kinds of nodes are implemented to sense the vibration and audio. In order to save the energy consumption, the sleeping scheduling is also designed for the monitoring system. According to the results, the designed nodes can be lived in the forest for 3 months at least.
{"title":"A novel real-time monitoring system for illegal logging events based on vibration and audio","authors":"Yu-Yan Chen, Jiun-Jian Liaw","doi":"10.1109/ICAWST.2017.8256503","DOIUrl":"https://doi.org/10.1109/ICAWST.2017.8256503","url":null,"abstract":"The Illegal logging (IL) has become an extremely important issue. We are trying to deploy the sensors in the forest. The sensors will send the data of illegal logging event while it happened. This paper is aiming to recognize the vibration of illegal logging events and the technique of illegal logging sound recognition. Two kinds of nodes are implemented to sense the vibration and audio. In order to save the energy consumption, the sleeping scheduling is also designed for the monitoring system. According to the results, the designed nodes can be lived in the forest for 3 months at least.","PeriodicalId":378618,"journal":{"name":"2017 IEEE 8th International Conference on Awareness Science and Technology (iCAST)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133906710","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-11-01DOI: 10.1109/ICAWST.2017.8256459
Yueh-Hsun Shih, C. Hsiao, W. Chu
Nowadays, the medical institutions still lack of real demonstration of meaningful use of personal healthcare services for healthcare. In this research, we planned to bring the personal healthcare service into real usage by taking the radiation oncology department as an example. The personal healthcare integration framework is composed of the following systems: A Single sign-on (SSO) portal, an e-learning platform (Moodle) and a radiation oncology information system (ARIATM). In this research, we integrate the patient's health information in the hospital and provide the right-time digital patient instruction service. There are 792 cancer patients registered in our system, and 85% of them agreed that their experience with the system were positive, and almost 4 in 5 said they are confident that they or their families had received proper cancer knowledge they needed during the cancer treatment period.
{"title":"Establishing the application of personal healthcare service system for cancer patients","authors":"Yueh-Hsun Shih, C. Hsiao, W. Chu","doi":"10.1109/ICAWST.2017.8256459","DOIUrl":"https://doi.org/10.1109/ICAWST.2017.8256459","url":null,"abstract":"Nowadays, the medical institutions still lack of real demonstration of meaningful use of personal healthcare services for healthcare. In this research, we planned to bring the personal healthcare service into real usage by taking the radiation oncology department as an example. The personal healthcare integration framework is composed of the following systems: A Single sign-on (SSO) portal, an e-learning platform (Moodle) and a radiation oncology information system (ARIATM). In this research, we integrate the patient's health information in the hospital and provide the right-time digital patient instruction service. There are 792 cancer patients registered in our system, and 85% of them agreed that their experience with the system were positive, and almost 4 in 5 said they are confident that they or their families had received proper cancer knowledge they needed during the cancer treatment period.","PeriodicalId":378618,"journal":{"name":"2017 IEEE 8th International Conference on Awareness Science and Technology (iCAST)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114074899","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-11-01DOI: 10.1109/ICAWST.2017.8256463
C. Hsieh, Shih-Cheng Homg, Zen-Jun Huang, Qiangfu Zhao
Recently, single image haze removal has been investigated extensively. However, its performance is evaluated mainly based on subjective visual quality of recovered images. Several objective assessments have been attempted to evaluate haze removal schemes objectively, such as no-reference image quality model and edge-based assessments. Unfortunately, these objective assessments are not able to measure visual quality of recovered images appropriately, since the visual quality of recovered images is not concerned. Note that an objective assessment for haze removal should consider dehazing effect and distortions introduced during the haze removal process. In this paper, an objective assessment for haze removal based on two-objective optimization is presented where both dehazing effect and distortions of color and artifacts in recovered images are considered. The two indicators are combined with a weighted Euclidean distance. Two examples with two dehazing schemes are provided to justify the proposed objective assessment for haze removal. The simulation indicates that the objective results are consistent with their subjective visual quality of recovered images. It suggests that the proposed objective assessment may be applied to evaluate different haze removal schemes objectively.
{"title":"Objective haze removal assessment based (Two-objective optimization","authors":"C. Hsieh, Shih-Cheng Homg, Zen-Jun Huang, Qiangfu Zhao","doi":"10.1109/ICAWST.2017.8256463","DOIUrl":"https://doi.org/10.1109/ICAWST.2017.8256463","url":null,"abstract":"Recently, single image haze removal has been investigated extensively. However, its performance is evaluated mainly based on subjective visual quality of recovered images. Several objective assessments have been attempted to evaluate haze removal schemes objectively, such as no-reference image quality model and edge-based assessments. Unfortunately, these objective assessments are not able to measure visual quality of recovered images appropriately, since the visual quality of recovered images is not concerned. Note that an objective assessment for haze removal should consider dehazing effect and distortions introduced during the haze removal process. In this paper, an objective assessment for haze removal based on two-objective optimization is presented where both dehazing effect and distortions of color and artifacts in recovered images are considered. The two indicators are combined with a weighted Euclidean distance. Two examples with two dehazing schemes are provided to justify the proposed objective assessment for haze removal. The simulation indicates that the objective results are consistent with their subjective visual quality of recovered images. It suggests that the proposed objective assessment may be applied to evaluate different haze removal schemes objectively.","PeriodicalId":378618,"journal":{"name":"2017 IEEE 8th International Conference on Awareness Science and Technology (iCAST)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121745318","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：