MS BMP specification issue

Wojciech Sobiesiak 96

Hello.

I have some question about BMP specification, been talking to my very good friend GPT and he couldn't help with it.

Question is

What is the purpose of this 0 , 0 after color arrays (2x2 pixels)

unsigned char tablica[] = {66,77,70,0,0,0,0,0,0,0,54,0,0,0,40,0,0,0,2,0,0,0,2,0,0,0,1,0,24,0,0,0,0,0,16,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,255,255,255,255,255,255,0,0,255,255,255,255,255,255,0,0,};

When I write 30px x 30px - I need to write additional 60 bytes.

I want to create hex-dec-binary bmp editor in php and realy need to understand what's going on :(

And do I understad that red pixel is at the right side of pixels value (B,G,R)?

Tom Jebo 1,996 Reputation points Microsoft Employee

2023-09-22T23:38:28.2133333+00:00

Hi @Wojciech Sobiesiak

The BMP file format is not covered under the Open Specifications documents but you can find a detailed description here that might help you:

https://en.wikipedia.org/wiki/BMP_file_format#Color_table

Best regards,
Tom Jebo
Microsoft Open Specifications Support
Wojciech Sobiesiak 96 Reputation points

2023-09-23T14:56:40.8966667+00:00

So spent so much time creating MSDN and now You tell me to visit wikipedia?

MSDN was created as I remember from early 2000.

Is M to be closed?
Tom Jebo 1,996 Reputation points Microsoft Employee

2023-09-23T19:20:59.2633333+00:00

Hi @Wojciech Sobiesiak

Since there isn't a formal specification for BMP, I've added the Windows API - Win32 tag. The BMP structures are documented in the Windows API documentation and one of our SDK support team might be more appropriate to able help you out.

For future reference, the Windows Open Specifications tag requires that you reference the document within the following Open Specifications library with which your question pertains:

Windows Open Specifications

I've removed the Windows Open Specification tag since BMP is not described in any of those specifications.

Best regards,
Tom Jebo
Microsoft Open Specifications Support

2 answers

Viorel 118.4K Reputation points

2023-09-23T17:38:44.99+00:00

I think that 0,0 represents the gaps between rows of pixel data. When the width is 2 and the image requires 24 bits per pixels, which is three bytes, then the width is 6 bytes. This width is rounded up to a four-byte boundary by padding. (Mentioned in Wikipedia too). The rounded width is 8 bytes, therefore the sequences of pixel data are followed by 0, 0.

The rows that include pixel data and gaps (if required) are called “strides” or “scan lines”.

The gaps appear in case of 30x30 image too.

Probably there is a justification for such rounding, maybe related to optimizations for typical hardware.
Please sign in to rate this answer.

1 person found this answer helpful.
Wojciech Sobiesiak 96 Reputation points

2023-09-24T03:40:47.68+00:00

I'm not sure if it is not used to fill rows in data that is not pixel-byte size.16 bits. https://learn.microsoft.com/en-us/windows/win32/medfound/image-stride "When a video image is stored in memory, the memory buffer might contain extra padding bytes after each row of pixels. The padding bytes affect how the image is stored in memory, but do not affect how the image is displayed." - question is where information about this padding is, I need to know when to add this 2 bytes because I want to create bmp file manually.

Xiaopo Yang - MSFT 12,726 Reputation points Microsoft Vendor

2023-09-25T23:50:40.41+00:00

@Wojciech Sobiesiak, does Calculating Surface Stride work for you?

stride = ((((biWidth * biBitCount) + 31) & ~31) >> 3); biSizeImage = abs(biHeight) * stride;

See Bitmap Structures , Capturing an Image for more information.

RGB images are saved as RGB as Image Stride says.
Sign in to comment

Use comments to ask for clarification, additional information, or improvements to the question.
Wojciech Sobiesiak 96 Reputation points

2023-09-26T03:53:17.62+00:00

cannot post answer here.

Xiaopo is this correct?

[http://infinityhost.ct8.pl/a/bmp_answer.html]

OS shows 2,74 KB (bytes: 2 814)

GPT method Image size: 2760 bytes

GPT - "Certainly! To create a BMP file where there are no additional 2 bytes of padding after each row, you'll need to make sure that the width of the image (in pixels) multiplied by the bits per pixel is divisible evenly by 8.

Let's say you want to create a 30x30 pixel image with 24 bits per pixel and no additional padding. Here's the calculation:

Width: 30 pixels Height: 30 pixels Color depth: 24 bits per pixel

Size of one row (in bits): 30 pixels * 24 bits per pixel = 720 bits

Since 1 byte = 8 bits, size of one row (in bytes): 720 bits / 8 = 90 bytes

Total size of image (without padding): 90 bytes/row * 30 rows = 2700 bytes

So, for a 30x30 pixel image with 24 bits per pixel and no additional padding, the size of the BMP file would be 2700 bytes."

Me after checking
"Image size: 2760 bytes -------------------------------- Process exited after 0.03797 seconds with return value 0 Press any key to continue . . ."

GPT "The result you're getting, 2760 bytes, is likely due to additional padding being added.

In the case of BMP images, the size of each row is typically rounded up to the nearest multiple of 4 bytes (32 bits). This is to ensure proper alignment for memory access.

Since your image has a width of 30 pixels and each pixel is represented using 24 bits (3 bytes), the calculated size of one row would be 90 bytes. However, to meet the alignment requirement, an additional 2 bytes of padding are added, resulting in a total row size of 92 bytes.

So, for a 30x30 pixel image with 24 bits per pixel, the actual size with padding would be:"

But OS still reports 2814 B.
Please sign in to rate this answer.

1 person found this answer helpful.
Xiaopo Yang - MSFT 12,726 Reputation points Microsoft Vendor

2023-09-26T05:22:35.2266667+00:00

Yes, the calculation is right but note as Capturing an Image says,

// Add the size of the headers to the size of the bitmap to get the total file size. dwSizeofDIB = dwBmpSize + sizeof(BITMAPFILEHEADER) + sizeof(BITMAPINFOHEADER); // Offset to where the actual bitmap bits start. bmfHeader.bfOffBits = (DWORD)sizeof(BITMAPFILEHEADER) + (DWORD)sizeof(BITMAPINFOHEADER); // Size of the file. bmfHeader.bfSize = dwSizeofDIB; ``` 2760+14+40=2814

Xiaopo Yang - MSFT 12,726 Reputation points Microsoft Vendor

2023-09-27T05:49:27.16+00:00

@Wojciech Sobiesiak, any update?

Wojciech Sobiesiak 96 Reputation points

2023-09-27T08:07:02.18+00:00

Xiaopo just need a little time, to rethink it, and I'm not goingh throgh "Capturing as image" source code. It would be very easy if MS Paint had an option of creating image from command promp( GPT - "As of my last knowledge update in September 2021, Microsoft Paint (MS Paint) does not have a built-in feature to create images from text prompts. " ) I would just create 100 different files, checked where these additional 2 bytes are, and know everything. Or It also would be very easy if Microsoft show source code of MS Paint, so I would modify it and use. Now I have many task to do and need to finish them, but soon will be back to this subject. I don't know how to handle this image handling I can do it with PHP or C++. So I will check it and then tell. Please be patient.

Viorel 118.4K Reputation points

2023-09-27T11:47:49.9366667+00:00

Are you still interested in the purpose of this 0, 0?

Wojciech Sobiesiak 96 Reputation points

2023-09-27T15:55:18.5233333+00:00

Viorel purpose is for correct alignment 32 bits memory blocks I was told. Just didn't test it yet. Now, I'm writin JS binary file C - writer that will at the end will be using php to write content, so topic stands in the corner of my room and is waitng to be added.

And as I wrote up there

"In the case of BMP images, the size of each row is typically rounded up to the nearest multiple of 4 bytes (32 bits). This is to ensure proper alignment for memory access."

Xiaopo Yang - MSFT 12,726 Reputation points Microsoft Vendor

2023-10-06T08:17:53.79+00:00

@Wojciech Sobiesiak, you can simply and easily verify that by using HEX editor beforehand. Capturing an Image also exposes the bits of the specified compatible which you can check in memory.

Xiaopo Yang - MSFT 12,726 Reputation points Microsoft Vendor

2023-11-22T03:11:58.94+00:00

stride = ((((biWidth * biBitCount) + 31) & ~31) >> 3); biSizeImage = abs(biHeight) * stride;

The total size is 30*92+14+40=2814. @Wojciech Sobiesiak, any update?

Wojciech Sobiesiak 96 Reputation points

2023-11-22T14:05:43.91+00:00

Xiaopo I had to delay this BMP issue. I've created some product, tried to introduce it to the world and see there is need to create market for it. And actually I don't think I'm able to do it without mixing it with service(s). And to do this I'm trying to take as many actions as it is possible to gather as much information as it is possible and expand my consciousness, prepare right methods. So graphics now is put on the shelf and waits till be most usefull part of some bigger project.
Sign in to comment

Use comments to ask for clarification, additional information, or improvements to the question.

Share via

MS BMP specification issue

2 answers

Your answer