CBIR using content frequency and colour features

Little studies have been done on morphology of medicinal plants seeds. This paper presents an automatic system for medicinal plant seed identification and evaluates the influence of colour features on seed identification. Six colour features (means of red, green and blue colours of the seed surface, as well as means of hue, intensity and saturation) were extracted by algorithm and applied as network input. Different combinations of colour features (one, two three, four, five and six colour features) were used to find out the most accurate combination for seed identification. Results showed that the six colour feature was the most accurate combination for seed identification (99.184% and 87.719% for training and test of neural network respectively). One colour feature had the lowest average accuracy values for seed identification (3.120% and 2.771%). In general, increasing the number of colour features increased the total average of accuracy values.

Download Full-text

Incorporating Colour Information for Computer-Aided Diagnosis of Melanoma from Dermoscopy Images: A Retrospective Survey and Critical Analysis

International Journal of Biomedical Imaging ◽

10.1155/2016/4868305 ◽

2016 ◽

Vol 2016 ◽

pp. 1-18 ◽

Cited By ~ 6

Author(s):

Ali Madooei ◽

Mark S. Drew

Keyword(s):

Critical Analysis ◽

Research Direction ◽

Semantic Features ◽

Retrospective Survey ◽

Statistical Measures ◽

Skin Cancers ◽

Life Threatening ◽

Lesion Analysis ◽

Colour Features ◽

High Level

Cutaneous melanoma is the most life-threatening form of skin cancer. Although advanced melanoma is often considered as incurable, if detected and excised early, the prognosis is promising. Today, clinicians use computer vision in an increasing number of applications to aid early detection of melanoma through dermatological image analysis (dermoscopy images, in particular). Colour assessment is essential for the clinical diagnosis of skin cancers. Due to this diagnostic importance, many studies have either focused on or employed colour features as a constituent part of their skin lesion analysis systems. These studies range from using low-level colour features, such as simple statistical measures of colours occurring in the lesion, to availing themselves of high-level semantic features such as the presence of blue-white veil, globules, or colour variegation in the lesion. This paper provides a retrospective survey and critical analysis of contributions in this research direction.

Download Full-text

Content based image retrieval with multi-channel LBP and colour features

International Journal of Applied Pattern Recognition ◽

10.1504/ijapr.2020.10033780 ◽

2020 ◽

Vol 6 (2) ◽

pp. 177

Author(s):

M.O. Divya ◽

E.R. Vimina

Keyword(s):

Image Retrieval ◽

Content Based Image Retrieval ◽

Colour Features

Download Full-text

Effects of target attributes on children's patterns of referential under- and over-specification

Journal of Child Language ◽

10.1017/s0305000915000367 ◽

2015 ◽

Vol 43 (4) ◽

pp. 867-889

Author(s):

MONIQUE CHAREST ◽

JUDITH R. JOHNSTON

Keyword(s):

Referential Communication ◽

Verbal Task ◽

Future Research ◽

Performance Potential ◽

Reasoning Task ◽

Verbal Reasoning ◽

Target Dimension ◽

Communication Task ◽

Colour Features ◽

Target Attributes

ABSTRACTWe examined the effects of object attributes on children's descriptive patterns in a referential communication task. Thirty preschoolers described object pairs that were selected by the experimenter. The targets were defined by shared size or colour, and differed on the non-target dimension in half of the trials. The children also completed a non-verbal reasoning task with analogous stimuli. They selected objects after observing the experimenter make a choice and inferring the basis for selection. In the communication task, the children produced fewer size than colour descriptions, particularly when the size targets differed in colour. They also over-specified colour features more often than size. They did not show a similar challenge identifying size relationships in the non-verbal task. The results support the conclusion that target attributes have a systematic influence on children's referential performance. Potential mechanisms for these effects, and directions for future research are discussed.

Download Full-text