Projects:2017s1-176 Smart Mirror with Raspberry Pi - Revision history

A1645963 at 03:40, 29 October 2017

2017-10-29T03:40:51Z

2017-10-29T03:40:11Z

2017-10-29T03:07:12Z

‎Face Recognition

2017-10-29T03:01:54Z

‎Face Recognition

2017-10-29T02:57:04Z

‎Future Work and Recommendations

2017-10-29T02:54:51Z

‎System Description

2017-10-29T02:54:14Z

‎System Description

2017-10-29T02:53:42Z

‎Background

2017-10-29T02:51:52Z

2017-10-29T02:16:19Z

‎System Description

@@ Line 51: / Line 51: @@
 The face detection and recognition algorithms tested were the Viola-Jones algorithm, Eigen-face method, Local Binary Pattern (LBP) algorithm, and Histogram of Oriented Gradients (HOG) with Neural Network. These were tested on Matlab and Python, using the FERET Sep96 testing technique.
-The test algorithms
+The Local Binary
 Pattern (LBP) Histogram and Viola-Jones algorithms
 performed best, and were selected for the Android
 implementation. The LBP algorithm achieved a
 recognition accuracy rate of 93%, and Viola-Jones achieved a detection accuracy of 97.9%.
 [[File:Lbp.jpg|300px|thumb|Figure 2. LBP encoding of an image]]
 == Voice Recognition ==

@@ Line 59: / Line 59: @@
 LBP works by splitting an image into neighbourhoods of pixels, and compares the intensity of the centre pixel to the surrounding ones. Depending on if the intensity of the centre pixel is greater or lower than the surrounding pixel, the pixel in the neighbourhood is assigned a binary value. The binary encodings of the neighbourhood pixels are concatenated to create a binary encoding of the entire pixel neighbourhood, which are then combined with the encodings of other neighbourhoods to create a histogram representation. The histograms of different images are compared to determine if they contain the same face.
 == Voice Recognition ==
@@ Line 87: / Line 90: @@
 == Problems Encountered ==
-HMM Matlab...
+During the implementation of HMM on the Matlab, some problems occurred. Since voice recognition based on HMM also uses Gaussian probability distribution, the multi-dimension probability density function is involved. With the inappropriate implementation of probability density function, the HMM did not work properly on Matlab. Combining Gaussian distribution and HMM was failed, which resulted in the problem of implementing voice recognition based on HMM on the Matlab.
 == Future Work and Recommendations ==

@@ Line 58: / Line 58: @@
 recognition accuracy rate of 93%, and Viola-Jones achieved a detection accuracy of 97.9%.
-LBP works by splitting an image into neighbourhoods of pixels, and compares the intensity of the centre pixel to the surrounding ones. Depending on if the intensity of the centre pixel is greater or lower than the surrounding pixel, the pixel in the neighbourhood is assigned a binary value. The binary encodings of the neighbourhood pixels are concatenated to create a binary encoding of the entire pixel neighbourhood
+LBP works by splitting an image into neighbourhoods of pixels, and compares the intensity of the centre pixel to the surrounding ones. Depending on if the intensity of the centre pixel is greater or lower than the surrounding pixel, the pixel in the neighbourhood is assigned a binary value. The binary encodings of the neighbourhood pixels are concatenated to create a binary encoding of the entire pixel neighbourhood, which are then combined with the encodings of other neighbourhoods to create a histogram representation. The histograms of different images are compared to determine if they contain the same face.
 == Voice Recognition ==

@@ Line 57: / Line 57: @@
 implementation. The LBP algorithm achieved a
 recognition accuracy rate of 93%, and Viola-Jones achieved a detection accuracy of 97.9%.
 == Voice Recognition ==

@@ Line 94: / Line 94: @@
 Similarly, the research, tests and development made for the face recognition aspect can be used to to incorporate face
 recognition, and other functionality such as multiuser
-capability into the system, and to integrate
+capability into the system.
 the device into a smart home system.

@@ Line 22: / Line 22: @@
 == System Description ==
 Both voice and image streams are obtained from the
@@ Line 28: / Line 30: @@
 face is identified, the device is unlocked, otherwise
 access to smart mirror is denied.
 Voice commands are processed once the device is

@@ Line 29: / Line 29: @@
 access to smart mirror is denied.
-[[File:System_desc.jpg|300px|thumb|captionnnnn]]
+[[File:System_desc.jpg|300px|thumb|Figure 1. System flow diagram]]
 Voice commands are processed once the device is

@@ Line 8: / Line 8: @@
 There have been many smart mirror projects conducted by others. They have predominantly used the Python and C programming languages to develop the software for their mirrors, and used operating systems such as Raspbian and Ubuntu. These mirrors are able to show the basic GUI and other information updated from website, such as weather and links of latest news. In addition, some smart mirror projects have voice control as well, which is supported by Amazon Alexa.
-Our primary aim  is to be incorporate face recognition technology into a smart mirror. We do not believe this has been done before as part of previous smart mirror projects. The secondary goal is to incorporate voice control. We also intend on using Android OS on the Raspberry Pi, and utilise user usage behaviour to customise their home screen.
+Our primary aim  was to incorporate face and voice recognition technology into a smart mirror. To the best of our knowledge, this had not been done before as part of previous smart mirror projects. We also desired to use Android OS on the Raspberry Pi, and utilise user usage behaviour to customise their home screen.
 == Motivation ==

@@ Line 39: / Line 39: @@
 == Face Recognition ==
-Several face detection & recognition algorithms were
+Zhao et al. provided a critical survey of still and video based facial recognition research [2]. They offer some insights into the studies of machine recognition of faces. The authors establish that the problem of automatic facial recognition involves three key steps [2]:
-tested using Matlab and Python. The test algorithms
-followed the flow diagram in Fig 4. The Local Binary
+• detection and normalisation of faces,
 Pattern (LBP) Histogram and Viola-Jones algorithms
 performed best, and were selected for the Android
 implementation. The LBP algorithm achieved a
-recognition accuracy rate of 93%.
+recognition accuracy rate of 93%, and Viola-Jones achieved a detection accuracy of 97.9%.
 == Voice Recognition ==