Gesture Recognition and Hand Tracking for Anti-Counterfeit Palmvein Recognition

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

The paper presented is to recognize the hand gesture and track hand for palm vein recognition in infrared  environment, in which the results explicitly prove the hand gesture recognition and the latter. However, the palm vien scanned, or recognized is not explicitly evident in the results provided and this questions on the contribution made. Further, there is no quantitative or qualitatively analysis carried to validate the performance of the system developed or proposed.  Hence, the paper needs to be improved to substantially support the proposed system.

Comments on the Quality of English Language

Quality of English is satisfactory.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

There are two contributions of this paper as follows:

-A hand gesture recognition algorithm is developed in infrared environment. the hand gesture contours are extracted from infrared gesture images. Then a deep learning model is used to recognize the hand gestures from these contours; 

-A hand tracking algorithm is developed in infrared environment, which is based on the detection of key points. The hand tracking is conducted after gesture recognition, which prevents the escape of the hand from the camera view, so it ensures that the hand for palmvein recognition is the identical hand during gesture recognition

However, to me the paper is needed to revise based on following factors

- There is no figure to present "a hand gesture recognition algorithm" or "a hand tracking algorithm", thus, it should be provided the figures for that

- in section 4.3 (from page 7), there are many implemented experiments, but it is not clear to me the effects of condition such as light, or distance between camera and hand, please provide and discuss on that

- in page 6, "The initial learning rate is 0.0001" is stated, more explain and discussion on the reason the rate of 0.0001 should be added 

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

Comments and Suggestions for Authors

(1) The hand gesture recognition implemented in this paper is in a pure background. In the future,we will improve the method in a complex background. In addition, more different kinds of gestures will be collected to increase the diversity of hand gesture.

(2) Author should do more emphasizes on mathematical modelling of the proposed design/model.

(3) Author described only predefined model in the paper. It looks like a robotic model. More justification is required why your model or design is better than previously proposed models/designs.

(4) Novelty of the proposed model is not clear. Please provide more relevant justification regarding the same. 

(5) Some latest references should also be incorporated and compare the results with the existing results.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Comments and Suggestions for Authors

The response and amendments done can be accepted but there is always room for further improvement. 

Reviewer 2 Report

Comments and Suggestions for Authors

The revised manuscript has been addressed my comments, now it can be published