Environmental Microbiological Content-Based Image Retrieval System Using Internal Structure Histogram

Zou, Yan; Li, Chen; Boukhers, Zeyd; Shirahama, Kimiaki; Jiang, Tao; Grzegorzek, Marcin

doi:10.1007/978-3-319-26227-7_51

Cited by 10 publications

(7 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, as depicted in Figure. To discriminate structural properties of each segmented EM region, we use Internal Structure Histogram (ISH) that is a contour-based shape feature and invariant to rotation and colour changes [2]. ISH is extracted by equidistantly distributing sample points on the contour of the EM region.…”

Section: Double-stage Em-cbir Methodsmentioning

confidence: 99%

“…In this method, image segmentation, shape feature extraction and support vector machines are used to discriminate between regions of an interesting EM and the others. In [2], the characteristics of shapes in different segmented EM regions are represented by an edge-based feature descriptor and used for an image retrieval task.…”

Section: Related Workmentioning

confidence: 99%

“…However, these traditional methods are time-consuming and inefficient. To improve the search effectiveness of EM information, especially for complex EM images, we develop a Content-based Image Retrieval (CBIR) system (EM-CBIR) [2,3]. The system searches over a database to find EM images that are relevant to a query EM image.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Content-based Image Retrieval of Environmental Microorganisms Using Double-stage Optimisation-based Fusion

Zou

Shirahama

et al. 2017

Information Engineering Express

Self Cite

View full text Add to dashboard Cite

Environmental Microorganisms (EMs) are very tiny living beings which impact the entire biosphere by their environmental functions. Traditionally, a lot of manual efforts through morphological analysis using microscopes have been put on looking for EMs. However, these methods are time-consuming and laborious. To overcome this, we develop a Contentbased Image Retrieval (CBIR) system for the EM image retrieval task within a Doublestage Optimisation-based Fusion framework. In the first stage, in order to effectively use the colour information of EM images, a Multiple Colour Channel Fusion (MCCR) method based on a Particle Swarm Optimisation (PSO) is developed to search for similar database images to a query image using local features. In the second stage, in order to enhance the retrieval performance of the first stage, a retrieval method based on Immune Evolutionary Particle Swarm Optimisation -Shuffled Frog Leaping Algorithm (IEPSO-SFLA) is devised to further combine global features. Finally, the experimental result shows that our doublestage fusion method obtains a mean average precision of 35.87% for 21 classes of EMs, which is superior to the existing methods.

show abstract

Section: Double-stage Em-cbir Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Content-based Image Retrieval of Environmental Microorganisms Using Double-stage Optimisation-based Fusion

Zou

Shirahama

et al. 2017

Information Engineering Express

Self Cite

View full text Add to dashboard Cite

show abstract

“…Based on the above work, in visual dictionary learning, two pair-wise (Li et al 2015c) local features, BoVW generation and an early fusion approach are used to enhance the spatial information of the feature extraction, where the classification performance of the local feature is increased to 44.2% MAP. As an extension of the work in Li et al (2015a, b), semi-automatic and full-automatic EM image retrieval systems are introduced in Zou et al (2015Zou et al ( , 2016aZou et al ( , b, 2017, where image segmentation, global and local shape feature extraction, multiply coulour channel fusion, similarity matching, and weight optimisation methods are applied. In the experiment, 420 EM images (21 classes, each class 20 images) are tested, and finally a 33.9 and 27% MAP are obtained for semi-and full-automatic approaches, respectively.…”

Section: Overview Of Em Classificationmentioning

confidence: 99%

A survey for the applications of content-based microscopic image analysis in microorganism classification domains

Wang

2017

Artif Intell Rev

Self Cite

View full text Add to dashboard Cite

Microorganisms such as protozoa and bacteria play very important roles in many practical domains, like agriculture, industry and medicine. To explore functions of different categories of microorganisms is a fundamental work in biological studies, which can assist biologists and related scientists to get to know more properties, habits and characteristics of these tiny but obbligato living beings. However, taxonomy of microorganisms (microorganism classification) is traditionally investigated through morphological, chemical or physical analysis, which is time and money consuming. In order to overcome this, since the 1970s innovative content-based microscopic image analysis (CBMIA) approaches are introduced to microbiological fields. CBMIA methods classify microorganisms into different categories using multiple artificial intelligence approaches, such as machine vision, pattern recognition and machine learning algorithms. Furthermore, because CBMIA approaches are semior full-automatic computer-based methods, they are very efficient and labour cost saving, supporting a technical feasibility for microorganism classification in our current big data age. In this article, we review the development history of microorganism classification using CBMIA approaches with two crossed pipelines. In the first pipeline, all related works are grouped by their corresponding microorganism application domains. By this pipeline, it is easy for microbiologists to have an insight into each special application domain and find their interested applied CBMIA techniques. In the second pipeline, the related works in each application domain are reviewed by time periods. Using this pipeline, computer scientists can see the dynamic of technological development clearly and keep up with the future devel-

show abstract

“…Alternatively, it has been shown that Approximate nearest neighbor (ANN) methods could be a sufficient solution in many applications that aim at large-scale information search and retrieval [14]. Subsequently, ANN that utilizes the real-valued image features has been used for CBIR in large-scale biomedical image databases [4], [5]. However, the real-valued image representations become a critical bottleneck, because the storage requirement for these representations increases with the number of samples.…”

Section: Introductionmentioning

confidence: 99%

Deep Convolutional Hashing for Low-Dimensional Binary Embedding of Histopathological Images

Sapkota

Shi

Xing

et al. 2019

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

Compact binary representations of histopathology images using hashing methods provide efficient approximate nearest neighbor search for direct visual query in large-scale databases. They can be utilized to measure the probability of the abnormality of the query image based on the retrieved similar cases, thereby providing support for medical diagnosis. They also allow for efficient managing of large-scale image databases because of a low storage requirement. However, the effectiveness of binary representations heavily relies on the visual descriptors that represent the semantic information in the histopathological images. Traditional approaches with hand-crafted visual descriptors might fail due to significant variations in image appearance. Recently, deep learning architectures provide promising solutions to address this problem using effective semantic representations. In this paper, we propose a Deep Convolutional Hashing (DCH) method that can be trained "point-wise" to simultaneously learn both semantic and binary representations of histopathological images. Specifically, we propose a convolutional neural network (CNN) that introduces a latent binary encoding (LBE) layer for low dimensional feature embedding to learn binary codes. We design a joint optimization objective function that encourages the network to learn discriminative representations from the label information, and reduce the gap between the real-valued low dimensional embedded features and desired binary values. The binary encoding for new images can be obtained by forward propagating through the network and quantizing the output of the LBE layer. Experimental results on a large-scale histopathological image dataset demonstrate the effectiveness of the proposed method.

show abstract

Environmental Microbiological Content-Based Image Retrieval System Using Internal Structure Histogram

Cited by 10 publications

References 10 publications

Content-based Image Retrieval of Environmental Microorganisms Using Double-stage Optimisation-based Fusion

Content-based Image Retrieval of Environmental Microorganisms Using Double-stage Optimisation-based Fusion

A survey for the applications of content-based microscopic image analysis in microorganism classification domains

Deep Convolutional Hashing for Low-Dimensional Binary Embedding of Histopathological Images

Contact Info

Product

Resources

About