作者：
Kamada, ShinIchimura, TakumiIwasaki, TakashiPrefectural Univ Hiroshima
Res Org Reg Oriented Studies Adv Artificial Intelligence Project Res Ctr Minami Ku 1-1-71 Ujina Higashi Hiroshima 7348558 Japan Prefectural Univ Hiroshima
Res Org Reg Oriented Studies Adv Artificial Intelligence Project Res Ctr Fac Management & Informat SystMinami Ku 1-1-71 Ujina Higashi Hiroshima 7348558 Japan Mitsui Consultants Co Ltd
MCC Lab Infrastruct Syst Grp Shinagawa Ku Gate City Ohsaki West Tower 15F1-11-1 Osaki Tokyo 1410032 Japan
We have developed an adaptive structural Deep Belief Network (Adaptive DBN) that finds an optimal network structure in a self-organizing manner during learning. The Adaptive DBN is the hierarchical architecture where ...
详细信息
ISBN:
(纸本)9781728165417
We have developed an adaptive structural Deep Belief Network (Adaptive DBN) that finds an optimal network structure in a self-organizing manner during learning. The Adaptive DBN is the hierarchical architecture where each layer employs Adaptive Restricted Boltzmann machine (Adaptive RBM). The Adaptive RBM can find the appropriate number of hidden neurons during learning. The proposed method was applied to a concrete image benchmark data set SDNET2018 for crack detection. The dataset contains about 56,000 crack images for three types of concrete structures: bridge decks, walls, and paved roads. The fine-tuning method of the Adaptive DBN can show 99.7%, 99.7%, and 99.4% classification accuracy for three types of structures. However, we found the database included some wrong annotated data which cannot be judged from images by human experts. This paper discusses consideration that purses the major factor for the wrong cases and the removal of the adversarial examples from the dataset.
Over last few decades, mathematics has played a crucial role in developing efficient algorithms for Face recognition (FR) used in biometric systems. FR using machinelearning (ML) techniques has impacted FR systems tr...
详细信息
ISBN:
(纸本)9789811513381;9789811513374
Over last few decades, mathematics has played a crucial role in developing efficient algorithms for Face recognition (FR) used in biometric systems. FR using machinelearning (ML) techniques has impacted FR systems tremendously, towards efficient and accurate models for FR. Existing FR systems used in biometrics use ML techniques to learn patterns in the images by extracting various features from them and often require pre-processed face image data for the learning process. In this paper, we have used various pre-processing techniques and compared them in the deployed FR framework. It was observed that the steerable Pyramid (SP) filter was the most efficient pre-processing technique among all techniques used for pre-processing in this work. Though existing feature extraction methods such as SIFT (Scale-Invariant Feature Transform), SURF (Speeded-Up Robust Features), ORB (Oriented FAst and Rotated BRIEF) have been used in the past, they have not been accurate enough in various vision based biometric systems. Hence, a novel PSI (Pose Scale and Illumination) invariant SURF-RootSIFT technique is proposed by extending the well known SIFT-RootSIFT feature extraction technique which is achieved by calculating the Bhattacharya Coefficient between the feature vectors. A framework which uses the proposed novel feature extraction technique is deployed in this work. This paper demonstrates that the novel SURF-RootSIFT based framework is proven to perform more accurately and efficiently than the other techniques, with 99.65, 99.74 and 97.93% accuracy on the Grimace, Faces95 and Faces96 databases respectively.
image enhancement and segmentation are predominating methods in imageprocessing and are widely used in ophthalmology for the diagnosis of various eye diseases such as diabetic retinopathy, glaucoma. Es...
详细信息
The present work explains the design and implementation of the difference expansion method based reversible image watermarking using Xilinx System Generator and MATLAB. The method represents structural design for hidi...
详细信息
Case-based reasoning (CBR) is a technique which solves a problem using past experiences, where a case base stores these past experiences called cases. CBR is used to solve different kinds of problems where past inform...
详细信息
India is an agricultural country and this sector accounts for 18 percent of India's GDP. This sector is the backbone of the country and focuses on better yield by using pesticides and fertilizers to prevent plant ...
详细信息
This study reports a disease symptom classification algorithm using a proposed patternrecognition approach to individually localize early and late blight visual disease symptoms. The algorithm uses the pathological a...
详细信息
ISBN:
(纸本)9781728133775
This study reports a disease symptom classification algorithm using a proposed patternrecognition approach to individually localize early and late blight visual disease symptoms. The algorithm uses the pathological analogy hierarchy of the diseases to produce a novel homogeneous pattern localization, more informative to extract features that would be utilized for a machinelearning system to classify the two diseases in digital photographs of vegetable plants. One of the most significant advantages of the proposed pattern analysis is localizing symptomatic and necrotic regions based on pathological disease analogy using soft computing, with which the pattern of each disease manifestation along the leaf surface can be tracked and quantified for characterization. In the 1st phase of the experiment, individual symptomatic (R-S), necrotic (R-N), and blurred (R-B, in-between healthy and symptomatic) regions were identified, segmented, and quantified. The 2nd phase focuses on the extraction of pattern features for classification and severity estimation with a machinelearning classifier. The obtained results are encouraging, successfully localizing and quantifying individual disease lesions. This also indicates the enhanced applicability of the proposed approach discriminating the two diseases based on their dissimilarity. It is also envisaged that the algorithm can be extended to other plant disease symptoms. Moreover, it provides opportunities for early identification and detection of subtle changes in plant growth, disease stage, and severity estimation to assisting crop diagnostics in precision agriculture.
In the current era of digitization, the worldwide healthcare service is a common practice;it enables the remote healthcare service with proper digits: diagnosis and medication. The main thread for the about service is...
详细信息
Texture investigation is a broad field of study with applications extending from remote sensing, satellite communication and autonomous systems to advanced systems such as robotics and machinelearning. Textural image...
详细信息
The present study investigates the effects of prototypical visualization approaches aimed at increasing the explainability of machinelearning systems in regard to perceived trustworthiness and observability. As the a...
详细信息
ISBN:
(数字)9783030503345
ISBN:
(纸本)9783030503338;9783030503345
The present study investigates the effects of prototypical visualization approaches aimed at increasing the explainability of machinelearning systems in regard to perceived trustworthiness and observability. As the amount of processes automated by artificial intelligence (AI) increases, so does the need to investigate users' perception. Previous research on explainable AI (XAI) tends to focus on technological optimization. The limited amount of empirical user research leaves key questions unanswered, such as which XAI designs actually improve perceived trustworthiness and observability. We assessed three different visual explanation approaches, consisting of either only a table with classification scores used for classification, or, additionally, one of two different backtraced visual explanations. In a within-subjects design with N = 83 we examined the effects on trust and observability in an online experiment. While observability benefitted from visual explanations, information-rich explanations also led to decreased trust. Explanations can support human-AI interaction, but differentiated effects on trust and observability have to be expected. The suitability of different explanatory approaches for individual AI applications should be further examined to ensure a high level of trust and observability in e.g. automated imageprocessing.
暂无评论