Dynamic splitting method for clothing-invariant human gait recognition

Ghebleh, Abbas; Moghadam, Mohsen Ebrahimi

doi:10.1109/iranianmvip.2015.7397534

Cited by 1 publication

(2 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to this, clothes and holding of an object poses tough challenges to the researchers over other covariate factors like shoes type, carrying condition, view angle etc. The earlier researchers have mainly concentrated on getting solution using techniques like GEI, LDA, SRC method and Random sub space method in spatial domain [4][5][6][7]. This gives us the motivation to analyse the features effectively in frequency domain.…”

Section: Revised Manuscript Received On November 15 2019mentioning

confidence: 99%

“…Each set of data is taken by 11 different cameras at an angle of 18°.GEI is used as feature and standard deviation is a statistic used to validate the results. The experiment uses 124 subjects each image of size 320 x 240 at 25Gps tested on CASIA gait dataset.Abbas Ghebleh, Mohsen Ebrahimi Modhadam [7] proposed an idea of splitting the silhouette into 3 regions to isolate the negative impact of clothing in effected region. Silhouette is split into 3 regions with 15% of height set as threshold.…”

Section: Iirelated Workmentioning

confidence: 99%

See 1 more Smart Citation

CHOG Based EFD for Geometric Shape Retrieval of Images for Cloth and Object Invariant Gait Recognition

Rayangoudar*,

Nagraj

2019

IJRTE

View full text Add to dashboard Cite

Gait refers to person identification based on the observation of human walking style. One of the prominent hurdles in gait recognition is, the challenges posed by change in apparels like clothes and object held by the subject. The paper explores the feature extraction techniques like CHOG and Elliptical Fourier Descriptors in spatial and frequency domain respectively to mitigate this negative impact on gait recognition. The CHOG behavioural feature extraction technique is used to capture the effective distribution of local gradient on gait sequence images. Further the Elliptical Fourier Descriptor (EFD) is found in frequency domain to access the geometric characteristics of a spatial domain image. The work is carried out on 36 subjects with 5 different apparels and 3 different objects each with 6 gait cycles from standard dataset CASIA SET – B and CMU - MoBo. SVM classifier is used to effectively discriminate the gait cycle patterns using optimal hyper plane. The results obtained have given an improvement of 7% to 24% increase in gait recognition over earlier techniques like GEI, CDA, LDA, ENTROPY, static and dynamic region splitting.

show abstract

Section: Revised Manuscript Received On November 15 2019mentioning

confidence: 99%

Section: Iirelated Workmentioning

confidence: 99%