Automatic image annotation via label transfer in the semantic space

Uricchio, Tiberio; Ballan, Lamberto; Seidenari, Lorenzo; Bimbo, Alberto Del

doi:10.1016/j.patcog.2017.05.019

Cited by 78 publications

(49 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Content-Based Image Retrieval approach automatically retrieves and index , 0 (2019) MATEC Web of Conferences https://doi.org/10.1051/matecconf/20192 255 1003 5501003 EAAI Conference 2018 different low-level features (colour, shape and texture) [5][6]. The need for large-scale image dataset annotation introduced the concept of Automatically Image Annotation (AIA) [7][8][9][10]. The AIA technique contains the good characteristics (advantages) from both traditional (text based and CBIR) annotated techniques through the keyword searching based on image content.…”

Section: Text-based Approach 2 Content-based Image Retrieval (Cbir) mentioning

confidence: 99%

Automatic Image Annotation for Small and Ad hoc Intelligent Applications using Raspberry Pi

et al. 2019

View full text Add to dashboard Cite

The cutting-edge technology Machine Learning (ML) is successfully applied for Business Intelligence. Among the various pre-processing steps of ML, Automatic Image Annotation (also known as automatic image tagging or linguistic indexing) is the process in which a computer system automatically assigns metadata in the form of captioning or keywords to a digital image. Automatic Image Annotation (AIA) methods (which have appeared during the last several years) make a large use of many ML approaches. Clustering and classification methods are most frequently applied to annotate images. In addition, these proposed solutions require a high computational infrastructure. However, certain real-time applications (small and ad-hoc intelligent applications) for example, autonomous small robots, gadgets, drone etc. have limited computational processing capacity. These small and ad-hoc applications demand a more dynamic and portable way to automatically annotate data and then perform ML tasks (Classification, clustering etc.) in real time using limited computational power and hardware resources. Through a comprehensive literature study we found that most image pre-processing algorithms and ML tasks are computationally intensive, and it can be challenging to run them on an embedded platform with acceptable frame rates. However, Raspberry Pi is sufficient for AIA and ML tasks that are relevant to small and ad-hoc intelligent applications. In addition, few critical intelligent applications (which require high computational resources, for example, Deep Learning using huge dataset) are only feasible to run on more powerful hardware resources. In this study, we present the framework of “Automatic Image Annotation for Small and Ad-hoc Intelligent Application using Raspberry Pi” and propose the low-cost infrastructures (single node and multi node using Raspberry Pi) and software module (for Raspberry Pi) to perform AIA and ML tasks in real time for small and ad-hoc intelligent applications. The integration of both AIA and ML tasks in a single software module (with in Raspberry Pi) is challenging. This study will helpful towards the improvement in various practical applications areas relevant to small intelligent autonomous systems.

show abstract

Section: Text-based Approach 2 Content-based Image Retrieval (Cbir) mentioning

confidence: 99%

Automatic Image Annotation for Small and Ad hoc Intelligent Applications using Raspberry Pi

et al. 2019

View full text Add to dashboard Cite

show abstract

“…In practice, it can increase the training intensity of low-frequency keywords for image samples in order to enhance the generalization performance of the whole model. For addressing this problem, we introduce an ANN based Auto-encoder method, which is used for unsupervised learning [2], [3]. The aim of an auto-encoder is to learn a representation for a set of data, typically for the purpose of dimensionality reduction.…”

Section: ) Balanced/skewed Distribution Abstractmentioning

confidence: 99%

“…In the AIA, the main idea is to automatically learn the semantic concept models from a huge number of image samples and utilize the conceptual models to label new images with proper tags [1]. The AIA has a lot of applications in various fields including access, search, and navigate the huge amount of visual data which stored in online or offline data sources, image manipulation and annotation application that used on a mobile device, [2]- [4]. The typical image annotation approaches rely on human viewpoints and the performance of them is highly dependent on the inefficient manual operations.…”

Section: Introductionmentioning

confidence: 99%

An Effective Automatic Image Annotation Model Via Attention Model and Data Equilibrium

Vatani¹,

Ahvanooey²,

Rahimi³

2018

ijacsa

View full text Add to dashboard Cite

Nowadays, a huge number of images are available. However, retrieving a required image for an ordinary user is a challenging task in computer vision systems. During the past two decades, many types of research have been introduced to improve the performance of the automatic annotation of images, which are traditionally focused on content-based image retrieval. Although, recent research demonstrates that there is a semantic gap between content-based image retrieval and image semantics understandable by humans. As a result, existing research in this area has caused to bridge the semantic gap between low-level image features and high-level semantics. The conventional method of bridging the semantic gap is through the automatic image annotation (AIA) that extracts semantic features using machine learning techniques. In this paper, we propose a novel AIA model based on the deep learning feature extraction method. The proposed model has three phases, including a feature extractor, a tag generator, and an image annotator. First, the proposed model extracts automatically the high and low-level features based on dual tree continues wavelet transform (DT-CWT), singular value decomposition, distribution of color ton, and the deep neural network. Moreover, the tag generator balances the dictionary of the annotated keywords by a new logentropy auto-encoder (LEAE) and then describes these keywords by word embedding. Finally, the annotator works based on the long-short-term memory (LSTM) network in order to obtain the importance degree of specific features of the image. The experiments conducted on two benchmark datasets confirm that the superiority of proposed model compared to the previous models in terms of performance criteria. Keywords-Automatic image annotation; attention model; skewed learning; deep learning, word embedding; log-entropy auto encoderI.

show abstract

“…And we use NDCG score to evaluate the performance of tag ranking compared to the baseline methods. Normalized Discounted Cumulative Gains (NDCG) [18] is a widely used measurement of tag ranking. The NDCG score is computed as (11), where ( ) is the relevance level of the i-th tag, K indicates that NDCG scores are calculated using the top K ranked tags, and z is a normalization constant ensuring the cumulative gain of NDCG score is 1.…”

Section: Tag Rankingmentioning

confidence: 99%

“…; [1,[13][14][15][16][17][18] study the tags relevance by textual information, for example [1,13,17,18] calculate the tags concurrence probability and analyze the semantical relevance between tags, [14] analyzes the ontological relationship for tags, [1,15] assume that the important tags' positions are prior to those irrelevant ones; [19,20] argue that tags are content-related to the image, and after comparing to other 3 factors, [19] concludes that the image content is the key factor for tag relevance learning.…”

Section: Introductionmentioning

confidence: 99%

Social Image Tag Relevance Learning based on Pixel Voting

Liu¹,

Ruan²,

Cai³

et al. 2018

dtcse

View full text Add to dashboard Cite

Social image platforms allow their users sharing and searching their photos based on images' tags. These tags are provided by different users. Inevitably, the tags are spontaneously ambiguous, and personalized. So, learning the relevance between tags and images is playing an important role in tag-based retrieval systems. Choosing visual neighbors for seed images as voters is a widely used method for learning tag relevance. However, most existing methods of choosing visual neighbors for seed images are based on the global features of the whole images, ignoring the local features. In this paper we propose a pixel voting method to choose the visual neighbors for seed images. Experiment shows that this method is a more natural way to measure the similarity of images. Based the selected neighbors we learn the tag relevance, and the experiment on the MIR Flickr dataset shows that our algorithm is effective in tag de-noising and tag ranking.

show abstract

Automatic image annotation via label transfer in the semantic space

Cited by 78 publications

References 53 publications

Automatic Image Annotation for Small and Ad hoc Intelligent Applications using Raspberry Pi

Automatic Image Annotation for Small and Ad hoc Intelligent Applications using Raspberry Pi

An Effective Automatic Image Annotation Model Via Attention Model and Data Equilibrium

Social Image Tag Relevance Learning based on Pixel Voting

Contact Info

Product

Resources

About