Introduction
In this article, we can learn how capture the bills of text images using this Money Management app. This app converts the images to quality visibility by zooming. So, whenever the user purchases some shopping or spending, he can capture the bill using this application and can save in memory.
So, I will provide the series of articles on this Money Management App, in upcoming articles I will integrate other Huawei Kits.
If you are new to this application, follow my previous articles.
Beginner: Manage the Budget using Room Database in Money Management Android app (Kotlin) – Part 3
ML Kit - Text Image Super-Resolution
The ML Kit - Text Image Super-Resolution feature of Huawei ML Kit. It provides better quality and visibility of old and blurred text on an image. When you take a photograph of a document from far or cannot properly adjust the focus, the text may not be clear. In this situation, it can zoom an image that contains the text up to three times and significantly improves the definition of the text.
Requirements
- Any operating system (MacOS, Linux and Windows).
- Must have a Huawei phone with HMS 4.0.0.300 or later.
- Must have a laptop or desktop with Android Studio, Jdk 1.8, SDK platform 26 and Gradle 4.6 and above installed.
- Minimum API Level 19 is required.
- Required EMUI 9.0.0 and later version devices.
How to integrate HMS Dependencies
First register as Huawei developer and complete identity verification in Huawei developers website, refer to register a Huawei ID.
Create a project in android studio, refer Creating an Android Studio Project.
Generate a SHA-256 certificate fingerprint.
To generate SHA-256 certificate fingerprint. On right-upper corner of android project click Gradle, choose Project Name > Tasks > android, and then click signingReport, as follows.
Note: Project Name depends on the user created name.
Download the agconnect-services.json file from App information, copy and paste in android Project under app directory, as follows.
Enter SHA-256 certificate fingerprint and click Save button, as follows.
Click Manage APIs tab and enable ML Kit.
Add the below maven URL in build.gradle(Project) file under the repositories of buildscript, dependencies and allprojects, refer Add Configuration.
maven { url 'http://developer.huawei.com/repo/' }
classpath 'com.huawei.agconnect:agcp:1.4.1.300'
- Add the below plugin and dependencies in build.gradle(Module) file.
apply plugin: 'com.huawei.agconnect'
// Huawei AGC
implementation 'com.huawei.agconnect:agconnect-core:1.5.0.300'
// Import the text image super-resolution base SDK.
implementation 'com.huawei.hms:ml-computer-vision-textimagesuperresolution:2.0.4.300'
// Import the text image super-resolution model package.
implementation 'com.huawei.hms:ml-computer-vision-textimagesuperresolution-model:2.0.4.300'
- Now Sync the gradle.
- Add the required permission to the AndroidManifest.xml file.
<uses-permission android:name="android.permission.CAMERA" />
<uses-permission android:name="android.permission.READ_EXTERNAL_STORAGE" />
Let us move to development
I have created a project on Android studio with empty activity let us start coding.
In the CaptureActivity.kt we can find the business logic.
class CaptureActivity : AppCompatActivity(), View.OnClickListener {
private var analyzer: MLTextImageSuperResolutionAnalyzer? = null
private val QUALITY = 1
private val ORIGINAL = 2
private var imageView: ImageView? = null
private var srcBitmap: Bitmap? = null
override fun onCreate(savedInstanceState: Bundle?) {
super.onCreate(savedInstanceState)
setContentView(R.layout.activity_capture)
imageView = findViewById(R.id.bill)
srcBitmap = BitmapFactory.decodeResource(resources, R.drawable.bill_1)
findViewById<View>(R.id.btn_quality).setOnClickListener(this)
findViewById<View>(R.id.btn_original).setOnClickListener(this)
createAnalyzer()
}
// Find the on click listeners
override fun onClick(v: View?) {
if (v!!.id == R.id.btn_quality) {
detectImage(QUALITY)
} else if (v.id == R.id.btn_original) {
detectImage(ORIGINAL)
}
}
private fun release() {
if (analyzer == null) {
return
}
analyzer!!.stop()
}
// Find the method to detect bills or text images
private fun detectImage(type: Int) {
if (type == ORIGINAL) {
setImage(srcBitmap!!)
return
}
if (analyzer == null) {
return
}
// Create an MLFrame by using the bitmap.
val frame = MLFrame.Creator().setBitmap(srcBitmap).create()
val task = analyzer!!.asyncAnalyseFrame(frame)
task.addOnSuccessListener { result -> // success.
Toast.makeText(applicationContext, "Success", Toast.LENGTH_LONG).show()
setImage(result.bitmap)
}.addOnFailureListener { e ->
// Failure
if (e is MLException) {
val mlException = e
// Get the error code, developers can give different page prompts according to the error code.
val errorCode = mlException.errCode
// Get the error message, developers can combine the error code to quickly locate the problem.
val errorMessage = mlException.message
Toast.makeText(applicationContext,"Error：$errorCode Message:$errorMessage", Toast.LENGTH_LONG).show()
// Log.e(TAG, "Error：$errorCode Message:$errorMessage")
} else {
// Other exception
Toast.makeText(applicationContext, "Failed：" + e.message, Toast.LENGTH_LONG).show()
// Log.e(TAG, e.message!!)
}
}
}
private fun setImage(bitmap: Bitmap) {
this@CaptureActivity.runOnUiThread(Runnable {
imageView!!.setImageBitmap(
bitmap
)
})
}
private fun createAnalyzer() {
analyzer = MLTextImageSuperResolutionAnalyzerFactory.getInstance().textImageSuperResolutionAnalyzer
}
override fun onDestroy() {
super.onDestroy()
if (srcBitmap != null) {
srcBitmap!!.recycle()
}
release()
}
}
In the activity_capture.xml we can create the UI screen.
<?xml version="1.0" encoding="utf-8"?>
<RelativeLayout xmlns:android="http://schemas.android.com/apk/res/android"
xmlns:app="http://schemas.android.com/apk/res-auto"
xmlns:tools="http://schemas.android.com/tools"
android:layout_width="match_parent"
android:layout_height="match_parent"
tools:context=".mlkit.CaptureActivity">
<LinearLayout
android:id="@+id/buttons"
android:layout_width="match_parent"
android:layout_height="wrap_content"
android:layout_alignParentBottom="true"
android:orientation="vertical"
tools:ignore="MissingConstraints">
<Button
android:id="@+id/btn_quality"
android:layout_width="match_parent"
android:layout_height="50dp"
android:layout_margin="15dp"
android:gravity="center"
android:textSize="19sp"
android:text="Quality"
android:textAllCaps="false"
android:textColor="@color/Red"
tools:ignore="HardcodedText" />
<Button
android:id="@+id/btn_original"
android:layout_width="match_parent"
android:layout_height="50dp"
android:layout_margin="15dp"
android:gravity="center"
android:text="Original"
android:textSize="19sp"
android:textAllCaps="false"
android:textColor="@color/Red"
tools:ignore="HardcodedText" />
</LinearLayout>
<ScrollView
android:layout_width="match_parent"
android:layout_height="match_parent"
android:layout_above="@+id/buttons"
android:layout_marginBottom="15dp">
<ImageView
android:id="@+id/bill"
android:layout_width="wrap_content"
android:layout_height="wrap_content"
android:layout_centerInParent="true"
android:layout_gravity="center"
tools:ignore="ObsoleteLayoutParam" />
</ScrollView>
</RelativeLayout>
Demo
Tips and Tricks
- Make sure you are already registered as Huawei developer.
- Set minSDK version to 19 or later, otherwise you will get AndriodManifest merge issue.
- Make sure you have added the agconnect-services.json file to app folder.
- Make sure you have added SHA-256 fingerprint without fail.
- Make sure all the dependencies are added properly.
Conclusion
In this article, we have learned about the Text Image Super-Resolution feature of Huawei ML Kit and its functionality. It provides better quality and visibility of old and blurred text on an image. It can zoom an image that contains the text up to three times and significantly improves the definition of the text.
Reference
ML Kit – Documentation
ML Kit – Training Video
Top comments (0)