Content-Based Image Retrieval (CBIR) method analyzes the content of an image and extracts the features to describe images, also called the image annotations (or called image labels). A machine learning (ML) algorithm ...
详细信息
ISBN:
(数字)9783319544724
ISBN:
(纸本)9783319544724
Content-Based Image Retrieval (CBIR) method analyzes the content of an image and extracts the features to describe images, also called the image annotations (or called image labels). A machine learning (ML) algorithm is commonly used to get the annotations, but it is a time-consuming process. In addition, the semantic gap is another problem in image labeling. To overcome the first difficulty, google cloud vision api is a solution because it can save much computational time. To resolve the second problem, a transformation method is defined for mapping the undefined terms by using the WordNet. In the experiments, a well-known dataset, Pascal VOC 2007, with 4952 testing figures is used and the cloudvisionapi on image labeling implemented by R language, called cloudvisionapi. At most ten labels of each image if the scores are over 50. Moreover, we compare the cloudvisionapi with well-known ML algorithms. This work found this api yield 42.4% mean average precision (mAP) among the 4,952 images. Our proposed approach is better than three well-known ML algorithms. Hence, this work could be extended to test other image datasets and as a benchmark method while evaluating the performances.
In an effort to increase the functional dependence for the visually impaired people, have identified the disadvantages and drawbacks in the present existing solutions and have tried to include the loopholes in the exi...
详细信息
Since the empathic processes are essential to the aesthetic experience, the empathy-enabling technology for behavioral sensing is gaining its popularity to support the study of anonymized viewers' cognition in art...
详细信息
ISBN:
(纸本)9783030316051;9783030316044
Since the empathic processes are essential to the aesthetic experience, the empathy-enabling technology for behavioral sensing is gaining its popularity to support the study of anonymized viewers' cognition in art appreciation. Because such behavior is highly dynamic and divergent among viewers, it is a challenge to observe the multiple dynamic features from the streaming data. In this study, we propose a vision sensor network (VSN) to support the visual interpretation of viewers' appreciation on visual arts. It firstly annotates the features in the captured frames based on cloudapi (here the google cloud vision api is used), and secondly the query on nested documents in MongoDB provides universal access to the annotated features. Comparing with the traditional approaches with subjective evidence, such as the questionnaire or social listening methods, the proposed VSN can interpret the visible behavior of viewers in real-time. In addition, it also has less selective bias because of more objective evidence being captured.
Gender Detection has numerous application in the field of authentication, security and surveillance systems, social platforms and social media. The proposed system describes gender detection based on Computer vision a...
详细信息
ISBN:
(纸本)9781538608074
Gender Detection has numerous application in the field of authentication, security and surveillance systems, social platforms and social media. The proposed system describes gender detection based on Computer vision and Machine Learning Approach using Convolutional Neural Network (CNN) which is used to extract various facial feature. First, the facial-extraction is investigated and best features are introduced which would be useful for training and testing the dataset. This learning representation is taken through the use of convolution neural network. Which reveals that the proposed system is tested across various challenging levels of face datasets and gives excellent performance efficiency of the system with gender detection rate for each of the database. This whole system is introduced by the simple and easy hardware implementation on Raspberry Pi programmed using Python.
In this paper, we propose a framework that uses latent information from Twitter images by employing the google cloud vision api platform aiming at enriching social analytics with semantics and textual information. Our...
详细信息
ISBN:
(纸本)9781728159195
In this paper, we propose a framework that uses latent information from Twitter images by employing the google cloud vision api platform aiming at enriching social analytics with semantics and textual information. Our study reveals that user-generated content, linked data as well as hidden concepts and textual information from social images can be highly considered for enriching social analytics. Finally, we publish our annotated dataset for further use and evaluation from our research community.
The appearance of images in social messages is continuously increasing, along with user engagement with that type of content. Analysis of social images can provide valuable latent information, often not present in the...
详细信息
The appearance of images in social messages is continuously increasing, along with user engagement with that type of content. Analysis of social images can provide valuable latent information, often not present in the social posts. In that direction, a framework is proposed exploiting latent information from Twitter images, by leveraging the google cloud vision api platform, aiming at enriching social analytics with semantics and hidden textual information. As validated by our experiments, social analytics can be further enriched by considering the combination of user-generated content, latent concepts, and textual data extracted from social images, along with linked data. Moreover, we employed word embedding techniques for investigating the usage of latent semantic information towards the identification of similar Twitter images, thereby showcasing that hidden textual information can improve such information retrieval tasks. Finally, we offer an open enhanced version of the annotated dataset described in this study with the aim of further adoption by the research community.
暂无评论