DIC-Median Filter Engine 2 Solved

1         Introduction
The median filter is a non-linear digital filtering technique, which is often used to remove noise from an image or signal. Such noise reduction is a typical preprocessing step to improve the results of later processing (for example, edge detection on an image). In this homework, please implement an median filter engine (MFE), which uses median filter to convolve the image. The specification and function of MFE circuit will be described in detail in the following section. 

2         Design Specifications
2.1      Block overview 
  

Fig. 1 – System operation flow

 

2.2      I/O Interface 
Name
I/O
Width
Description
clk
I
1
System clock signal. This system is synchronized with the positive edge of the clock.
reset
I
1
Active-high asynchronous reset signal.
ready
I
1
Grayscale image ready indication signal. When this
 
 
 
signal is high, the grayscale image memory is already prepared. MFE can start sending grayscale image address to obtain the data.
busy
O
1
System busy indication signal. When MFE receives high level ready signal and MFE is ready to start the calculation, this signal has to be set as high. After the calculation is completed and the result is completely output, set this signal to low and the testbench will start checking if the result is correct.
iaddr
O
14
The signal for grayscale image memory address, which is used to request grayscale image pixel date.
idata
I
8
Input grayscale image pixel data signal, which represents an 8 bits unsigned integer. The testbench will send the pixel data according to the address iaddr indicates.
data_rd
I
8
Result memory read data signal, which represents an 8 bits unsigned integer. This signal is used to send the result memory data to MFE circuit.
addr
O
14
Result memory read/write address.

This signal indicates which address of the result memory will be read or written.
data_wr
O
8
Result memory write data signal, which represents an 8 bits unsigned integer. The operation result of the MFE circuit is written to result memory using this signal.
wen
O
1
Result memory write enable signal.

When this signal is low (read), the data with address addr in result memory is sent by data_rd.

When this signal is high (write), the data sent by data_wr is written to the address addr in result memory.
 

           

2.3      Function Description 
Input Image:

 

                                                                    Fig. 2 – Circuit operation flow                                                                     

The size of the input image in this system is 128x128, which is stored in the grayscale image memory. The correspondence between each pixel of the grayscale image and memory arrangement is shown in Figure 4. In the operation process, the MFE circuit uses the iaddr signal to send the address of requested image data (as shown in Figure 3. t1 time point). After the negative edge of each clock, the pixel data at requested address will be sent into the MFE circuit by the idata signal (as shown in figure 3. t2 time point).

  

Fig. 3 – Timing diagram while reading grayscale image memory 

 

 

Fig. 4 – Arrangement mapping of input grayscale image and grayscale memory 

 

The first step of the system is to perform zero-padding on the image to avoid size-changing of the image when doing MFE operation. Then the padded image is convolved with median filter to obtain result image. After the calculation is finished, the busy signal should be set to 0, and then testbench will start the verification process.

  

Fig. 5 – The median filtering operation. 

In the reading phase, the addr signal represents the memory address of result memory to read and the data_rd signal will provide the data. wen signal should be set as low. The timing diagram of result memory reading operation is shown in figure 6.

In the writing phase, the addr signal informs the memory address to be written and the data_wr signal should provide the writing data. wen signal should be set as high. The timing diagram of result memory writing operation is shown in figure 7.  

  

Fig. 6 – Timing diagram of reading result memory.

 

  

Fig. 7 – Timing diagram of writing result memory.

 

3         Software Verification
You need to write a program to verify your circuit. You can write your program by using C, C++ and python. The requirements and functionality of this program should be as following:

1.      Be able to read any jpg image. The file path for reading has to be ./image.jpg.

2.      Convert RGB image to gray scale.

3.      Resize the image into 128x128.

4.      Add salt and pepper noise to the image.  

(You may set the probability of the noise to 0.02.)

5.      Process median filtering to the image with noise.

6.      Output the image with noise and the filtered image as img.dat and golden.dat, respectively. The format of the output files should be the same as the img.dat and golden.dat which TA gave. The output file should be able to be read by the testbench and simulate correctly.

7.      Please name your program in the format: main.c, main.cpp or main.py.