A template matching approach of one-shot-learning gesture recognition

Mahbub, Upal; Imtiaz, Hafiz; Roy, Tonmoy; Rahman, Md. Shafiur; Ahad, Md. Atiqur Rahman

doi:10.1016/j.patrec.2012.09.014

Cited by 43 publications

(17 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Learning materials available today already meet the needs of students of the theory curriculum but cannot lead students to develop a critical mindset to be able to apply the theory (Flores, Matkin, Burbach, Quinn, & Harding, 2012;Serdyukov, 2018). Students should be empowered, facilitated, motivated, and allowed to construct knowledge according to their interests and needs and give the freedom to learn by themselves (Mahbub, Imtiaz, Roy, Rahman, & Ahad, 2013). Therefore, learning material in the form of the module was developed in aiming to help the students understand the concept of theory but also common in doing scientific activities to dig their knowledge.…”

Section: Resultsmentioning

confidence: 99%

Ethnobotanical study of medicinal plants utilized by the Baduy tribe used as a learning resource

Khastini

Wahyuni

Saraswati

et al. 2019

JPBI

View full text Add to dashboard Cite

The existence of contextual learning resources has been known to be able to improve the meaningful learning, particularly biology learning. This research provides the information about the medicinal plant utilized by the Baduy tribe as well as its endeavour in developing the results obtained as a contextual-based module. This research and development was designed using 4D model by Thiagarajan, which was limited in three phases (define, design, and development). The data was collected using interview guideline, validation sheets, and students’ response questionnaires. The research findings inform that there were 67 species utilized by the Baduy tribe as the medicinal plants. These species belong to Spermatophyte and divided into 31 families. Furthermore, the validation results showed that the media developed was valid; in which the best component of module, based on students’ response, was its presentation (the mean value was 89.5%). It can be concluded that the media developed is feasible to use as learning resource.

show abstract

Section: Resultsmentioning

confidence: 99%

Ethnobotanical study of medicinal plants utilized by the Baduy tribe used as a learning resource

Khastini

Wahyuni

Saraswati

et al. 2019

JPBI

View full text Add to dashboard Cite

show abstract

“…Due to few target task samples, the relevant knowledge in source task is used as the target prior to construct the probability density function of the model parameters. In terms of the continuous motion images, Mahbub [53] adopts space-time describer to trace the motion and gestures of the images, form space depth image and extract the features by 2D FFT. Finally, the image gestures are recognized according to relevant coefficients.…”

Section: Related Work a One-shot Learning And Unsupervised Adaptmentioning

confidence: 99%

Single-Sample Face Recognition Based on LPP Feature Transfer

2016

View full text Add to dashboard Cite

Due to its wide applications in practice, face recognition has been an active research topic. With the availability of adequate training samples, many machine learning methods could yield high face recognition accuracy. However, under the circumstance of inadequate training samples, especially the extreme case of having only a single training sample, face recognition becomes challenging. How to deal with conflicting concerns of the small sample size and high dimensionality in one-sample face recognition is critical for its achievable recognition accuracy and feasibility in practice. Being different from conventional methods for global face recognition based on generalization ability promotion and local face recognition depending on image segmentation, a single-sample face recognition algorithm based on Locality Preserving Projection (LPP) feature transfer is proposed here. First, transfer sources are screened to obtain the selective sample source using the whitened cosine similarity metric. Secondly, we project the vectors of source faces and target faces into feature sub-space by LPP respectively, and calculate the feature transfer matrix to approximate the mapping relationship on source faces and target faces in subspace. Then, the feature transfer matrix is used on training samples to transfer the original macro characteristics to target macro characteristics. Finally, the nearest neighbor classifier is used for face recognition. Our results based on popular databases FERET, ORL and Yale demonstrate the superiority of the proposed LPP feature transfer based one-sample face recognition algorithm when compared with popular single-sample face recognition algorithms such as (PC) 2 A and Block FLDA.INDEX TERMS Feature extraction, transfer learning, one-sample, face recognition, locality preserving projection.

show abstract

“…A simple average template approach was the first baseline proposed by the organizers of the gesture recognition challenge, and it remained a difficult baseline to beat during the first weeks of the competition (Guyon et al, 2012). Mahbub et al (2012) proposed a template matching approach for one-shot learning gesture recognition, where three ways of generating templates were proposed (2D standard-deviation, Fourier-transform and MHIs). For recognition the authors used the correla-tion coefficient to compare templates and testing videos.…”

Section: Motion-based Representationsmentioning

confidence: 99%

Principal motion components for one-shot gesture recognition

Escalante

Guyon

Athitsos

et al. 2015

Pattern Anal Applic

View full text Add to dashboard Cite

International audienceThis paper introduces principal motion components (PMC), a new method for one-shot gesture recognition. In the considered scenario a single training video is available for each gesture to be recognized, which limits the application of traditional techniques (e.g., HMMs). In PMC, a 2D map of motion energy is obtained per each pair of consecutive frames in a video. Motion maps associated to a video are processed to obtain a PCA model, which is used for recognition under a reconstruction-error approach. The main benefits of the proposed approach are its simplicity, easiness of implementation, competitive performance and efficiency. We report experimental results in one-shot gesture recognition using the ChaLearn Gesture Dataset; a benchmark comprising more than 50,000 gestures, recorded as both RGB and depth video with a Kinect™camera. Results obtained with PMC are competitive with alternative methods proposed for the same data set

show abstract

A template matching approach of one-shot-learning gesture recognition

Cited by 43 publications

References 21 publications

Ethnobotanical study of medicinal plants utilized by the Baduy tribe used as a learning resource

Ethnobotanical study of medicinal plants utilized by the Baduy tribe used as a learning resource

Single-Sample Face Recognition Based on LPP Feature Transfer

Principal motion components for one-shot gesture recognition

Contact Info

Product

Resources

About