Semi-automatic Image Annotation Research Articles

SaLFIA: Semi-automatic Live Feeds Image Annotation Tool for Vehicle Classification Dataset

Deep learning’s reliance on abundant data with accurate annotations presents a significant drawback, as developing datasets is often time-consuming and costly for specific problems. To address this drawback, we propose a semi-automatic live-feed image annotation tool called saLFIA. Our case study utilized CCTV data from Indonesia’s toll roads as one of the sources for live-feed images. The primary contribution of saLFIA is a labeling tool designed to generate new datasets from public source images, focusing on vehicle classification using YOLOv3 and SSD algorithms. The evaluation results indicated that SSD achieved higher accuracy with fewer initial images, while YOLOv3 reached maximum accuracy with larger initial datasets, resulting in 8 misdetections out of 380 objects. The saLFIA tool simplifies the annotation process, presenting a labeling tool for creating annotated datasets in a single operation. saLFIA is available at URL https://github.com/gilangmantara/salfia.

Efficient Maize Tassel-Detection Method using UAV based remote sensing

Regular monitoring is worthwhile to maintain a healthy crop. Historically, the manual observation was used to monitor crops, which is time-consuming and often costly. The recent boom in the development of Unmanned Aerial Vehicles (UAVs) has established a quick and easy way to monitor crops. UAVs can cover a wide area in a few minutes and obtain useful crop information with different sensors such as RGB, multispectral, hyperspectral cameras. Simultaneously, Convolutional Neural Networks (CNNs) have been effectively used for various vision-based agricultural monitoring activities, such as flower detection, fruit counting, and yield estimation. However, Convolutional Neural Network (CNN) requires a massive amount of labeled data for training, which is not always easy to obtain. Especially in agriculture, generating labeled datasets is time-consuming and exhaustive since interest objects are typically small in size and large in number. This paper proposes a novel method using k-means clustering with adaptive thresholding for detecting maize crop tassels to address these issues. The qualitative and quantitative analysis of the proposed method reveals that our method performs close to reference approaches and has an advantage over computational complexity. The proposed method detected and counted tassels with precision: 0.97438, recall: 0.88132, and F1 Score: 0.92412. In addition, using maize tassel detection from UAV images as the task in this paper, we propose a semi-automatic image annotation method to create labeled datasets of the maize crop easily. Based on the proposed method, the developed tool can be used in conjunction with a machine learning model to provide initial annotations for a given image, modified further by the user. Our tool's performance analysis reveals promising savings in annotation time, enabling the rapid production of maize crop labeled datasets.

Shape annotation by semi-supervised fuzzy clustering

Image annotation is an important and challenging task when managing large image collections. In this paper, a fuzzy shape annotation approach for semi-automatic image annotation is presented. A fuzzy clustering process guided by partial supervision is applied to shapes represented by Fourier descriptors in order to derive a set of shape prototypes representative of a number of semantic categories. Next, prototypes are manually annotated by attaching textual labels related to semantic categories. Based on the labeled proto-types, a new shape is automatically labeled by associating a fuzzy set that provides membership degrees of the shape to all semantic categories. The proposed annotation approach provides an innovative indexing method for shape-based image retrieval. Indeed, shape prototypes represent an inter-mediate indexing level that allows a faster retrieval process since a query is matched against prototypes, instead of the whole shape database, resulting in a speed up of the retrieval. The proposed approach is tested on synthetic and real-word images in order to show its suitability.

Linked tag: image annotation using semantic relationships between image tags

State of the art image tagging systems are limited because they allow users to annotate image tags in noun form, which cannot fully express the semantics of image content. In this paper, we propose Linked Tag, a semi-automatic image annotation system that inserts semantic relationships between tags. The proposed annotation method connects image tags using predicate words that can capture the contexts in which the image tags are used. In particular, we exploit Linked Data such as DBPedia in order to connect the image tags with a property value. Compared with tag-based annotation and ontology-based annotation systems, Linked Tag eliminates a large amount of manual labor and enhances the semantic expression of image content. We also introduce two annotation-based applications on Linked Tag. First, we propose SPARQL query processing for image retrieval, which enables us to express visual appearance as well as semantic information. Second, we propose a novel tag-ranking algorithm based on the link analysis in the RDF annotation graph. Finally, we demonstrate the operation of our proposed system and analyze its efficacy.

Semi-automatic dynamic auxiliary-tag-aided image annotation

Image annotation is the foundation for many real-world applications. In the age of Web 2.0, image search and browsing are largely based on the tags of images. In this paper, we formulate image annotation as a multi-label learning problem, and develop a semi-automatic image annotation system. The presented system chooses proper words from a vocabulary as tags for a given image, and refines the tags with the help of the user's feedback. The refinement amounts to a novel multi-label learning framework, named Semi-Automatic Dynamic Auxiliary-Tag-Aided (SADATA), in which the classification result for one certain tag ( target tag) can be boosted by the classification results of a subset of the other tags ( auxiliary tags). The auxiliary tags, which have strong correlations with the target tag, are determined in terms of the normalized mutual information. We only select those tags whose correlations exceed a threshold as the auxiliary tags, so the auxiliary set is sparse. How much an auxiliary tag can contribute is dependent on the image, so we also build a probabilistic model conditioned on the auxiliary tag and the input image to adjust the weight of the auxiliary tag dynamically. For an given image, the user feedback on the tags corrects the outputs of the auxiliary classifiers and SADATA will recommend more proper tags next round. SADATA is evaluated on a large collection of Corel images. The experimental results validate the effectiveness of our dynamic auxiliary-tag-aided method. Furthermore, the performance also benefits from user feedbacks such that the annotation procedure can be significantly speeded up.