Comments (6)
@michealChin There is no such specification on the input images. If the images have their natural orientation, you are good to go. Image resizing and parsing are handled by the app, so you need not worry for that. Also, every ML model is prone to errors, hence it is important to mention that inaccuracies may be observed.
Great! I will spend some time to play around with the code. Have a nice day!
from facerecognition_with_facenet_android.
@michealChin Could you try using the abs
function in BitmapUtils.kt
like,
fun cropRectFromBitmap(source: Bitmap, rect: Rect ): Bitmap {
var width = rect.width()
var height = rect.height()
rect.left = if( rect.left > 0 ) rect.left else 0
rect.top = if( rect.top > 0 ) rect.top else 0
if ( (rect.left + width) > source.width ){
width = abs( source.width - rect.left )
}
if ( (rect.top + height ) > source.height ){
height = abs( source.height - rect.top )
}
val croppedBitmap = Bitmap.createBitmap( source , rect.left , rect.top , width , height )
// Uncomment the below line if you want to save the input image.
// BitmapUtils.saveBitmap( context , croppedBitmap , "source" )
return croppedBitmap
}
from facerecognition_with_facenet_android.
I call cropRectFromBitmap and pass in the image that located in the image folder and simply choose the Rect (0,0,100,100) and it successfully return me a crop bitmap without any exception. However Is this related to the apps crash with the error message I share in the post?
from facerecognition_with_facenet_android.
In some cases, source.width
< rect.left
which produces a negative number to be stored in width
.
from facerecognition_with_facenet_android.
I got two folder actually, each folder with one image. I remove one of the folder and the apps no longer crash, may I know what is the specification for the bitmap to be read correctly by this project? Image Size (width and height)? Image Type?
Another question, you mention that Facenet is not very accurate, but according to https://paperswithcode.com/sota/face-verification-on-labeled-faces-in-the Facenet rank number 2 with 99.63% accuracy.
Anyway, you did a great job! Really appreciate your effort!
from facerecognition_with_facenet_android.
@michealChin There is no such specification on the input images. If the images have their natural orientation, you are good to go. Image resizing and parsing are handled by the app, so you need not worry for that. Also, every ML model is prone to errors, hence it is important to mention that inaccuracies may be observed.
from facerecognition_with_facenet_android.
Related Issues (20)
- Error in FrameAnalyser.kt : Cannot copy to a TensorFlowLite tensor (input_1) with 307200 bytes from a Java Buffer with 150528 bytes HOT 4
- [Error] : Getting facelist.size as 0 in FrameAnalyser.kt HOT 12
- l2 Norm not working as expected. HOT 13
- I am getting same name for every image in the frame HOT 6
- [request] write detection log to a file
- [issue] Always assign a face even if the image does not exist. HOT 2
- How to train the facenet model HOT 2
- Works incorrectly in samsung A21s HOT 9
- Device orientation problem HOT 3
- bounding box overlay not showing properly. HOT 1
- Internal error: Failed to apply delegate with GpuDelegate HOT 3
- App is hanging with 300 Images HOT 3
- TfLiteGpuDelegate Invoke: GpuDelegate must run on the same thread HOT 3
- Multiple facial recognition in a single frameis not detecting properly HOT 2
- Works on phone but not on tablet HOT 1
- How to improve the accuracy of facenet ?
- Can the source of the photo not be from storage but from a photo link? HOT 2
- landscape orientation HOT 2
- Application of tflite models and how to convert them. HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from facerecognition_with_facenet_android.