Semantic Guided Interactive Image Retrieval for plant identification

Gonçalves, Filipe Marcel Fernandes; Guilherme, Ivan Rizzo; Pedronette, Daniel Carlos Guimarães

doi:10.1016/j.eswa.2017.08.035

Cited by 18 publications

(8 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Goncalves et al [27] have proposed, the combining contentbased image retrieval (CBIR) technique is suitable for diagram basing design, which is known as Semantic Interactive Image Retrieval (SIIR). It bolsters master recognizable proof undertakings, for example, to differentiate the angiosperm groups in plants is one of the scholar's jobs.…”

Section: Related Workmentioning

confidence: 99%

Enhancing Classifier Accuracy in Ayurvedic Medicinal Plants using WO-DNN

Keskar,

Maktedar

2019

IJEAT

View full text Add to dashboard Cite

Identification of right medicinal plants that goes in to the formation of a medicine is significant in ayurvedic medicinal industry. This paper focuses around the automatic identification proof of therapeutic plants that are regularly utilized in Ayurveda. The fundamental highlights required to distinguish a medicinal plant is its leaf shape, color and texture. In this paper, we propose efficient accurate classifier for ayurvedic medical plant identification (EAC-AMP) utilizing using hybrid optimal machine learning techniques. In EAC-AMP, image corners detect first and top, bottom leaf edges are computed by the improved edge detection algorithm. After preprocessing, the segmentation can achieve using spider optimization neural network (SONN), which segments leaf regions from an image. The time and frequency domain features are computed by the symbolic accurate approximation (SAX); other features shape features, color features and tooth features are computed by the two-dimensional binary phase encoding (2DBPE). Finally, a whale optimization with deep neural network (DNN) classifier is used to characterize the type of plants. Accuracy in identification of any ayurvedic plant leaf is achieved by understanding and extracting the plant features. The main objective of the proposed EAC-AMP approach is to increase the accuracy of classifier. MATLAB experimental analysis showed better results such as accuracy, sensitivity and specificity.

show abstract

Section: Related Workmentioning

confidence: 99%

Enhancing Classifier Accuracy in Ayurvedic Medicinal Plants using WO-DNN

Keskar,

Maktedar

2019

IJEAT

View full text Add to dashboard Cite

show abstract

“…In all the above-mentioned applications, we cannot resort to standard hashing techniques, given that even minimal alterations would make different copies untraceable. Similarly, it is not possible to rely on associated text, tags or taxonomies for retrieval, as done for instance in (Gonçalves et al, 2018), since they would likely change in different sites or devices where content is used. Images may be subject to digital forgery, with parts of one or more existing images combined to create fake ones.…”

Section: Introductionmentioning

confidence: 99%

Benchmarking unsupervised near-duplicate image detection

Morra

Lamberti

2019

Expert Systems with Applications

View full text Add to dashboard Cite

Unsupervised near-duplicate detection has many practical applications ranging from social media analysis and web-scale retrieval, to digital image forensics. It entails running a threshold-limited query on a set of descriptors extracted from the images, with the goal of identifying all possible near-duplicates, while limiting the false positives due to visually similar images. Since the rate of false alarms grows with the dataset size, a very high specificity is thus required, up to 1 − 10 −9 for realistic use cases; this important requirement, however, is often overlooked in literature. In recent years, descriptors based on deep convolutional neural networks have matched or surpassed traditional feature extraction methods in content-based image retrieval tasks. To the best of our knowledge, ours is the first attempt to establish the performance range of deep learning-based descriptors for unsupervised near-duplicate detection on a range of datasets, encompassing a broad spectrum of near-duplicate definitions. We leverage both established and new benchmarks, such as the Mir-Flick Near-Duplicate (MFND) dataset, in which a known ground truth is provided for all possible pairs over a general, large scale image collection. To compare the specificity of different descriptors, we reduce the problem of unsupervised detection to that of binary classification of near-duplicate vs. not-near-duplicate images. The latter can be conveniently characterized using Receiver Operating Curve (ROC). Our findings in general favor the choice of fine-tuning deep convolutional networks, as opposed to using off-the-shelf features, but differences at high specificity settings depend on the dataset and are often small. The best performance was observed on the MFND benchmark, achieving 96% sensitivity at a false positive rate of 1.43 × 10 −6 .

show abstract

“…This grand challenge is handled in many data data-intensive science applications including health informatics [5],social media [6], [7],image processing [8], web page analysis [9] etc. We in this research has focused towards exploring the solution of this challenge in the crime analysis domain,that mostly deals with unstructured text content.…”

Section: Introductionmentioning

confidence: 99%