Posted on

How to Integrate HUAWEI ML Kit’s Image Super-Resolution Capability

Have you ever been sent compressed images that have poor definition? Even when you zoom in, the image is still blurry. I recently received a ZIP file of travel photos from a trip I went on with a friend. After opening it, I found to my dismay that each image was either too dark, too dim, or too blurry. How am I going to show off with such terrible photos? So, I sought help from the Internet, and luckily, I came across HUAWEI ML Kit's image super-resolution capability. The amazing thing is that this SDK is free of charge and can be used with all Android phones. 

Background

ML Kit's image super-resolution capability is backed by a deep neural network and provides two super-resolution capabilities for mobile apps:

Posted on

How to Quickly Recognize Fake Faces

Introduction

Have you ever wondered whether unlocking your phone with facial recognition is really safe? What if someone masqueraded as you by using photos or videos of you, could your phone detect that it's not you in front of the camera? Well, thanks to ML Kit's liveness detection capability, it can! This feature accurately distinguishes between real faces and fake ones. Whether it’s a photo, video, or mask, liveness detection can immediately expose those fake faces! 

Application Scenarios

Liveness detection is generally used to perform a face match. First, it will determine whether the person in front of the camera is a real person, instead of a person holding a photo or a mask. Then, face match will compare the current face to the one it has on record, to see if they are the same person. Liveness detection is useful in a huge range of situations. For example, it can prevent people from unlocking your phone and accessing your personal information. 

Posted on

How to Implement Eye-Enlarging and Face-Shaping Functions Using HUAWEI ML Kit’s Face Detection Capability

Introduction

Sometimes, we can't help taking photos to capture unforgettable moments in life. But most of us are not professional photographers or models, so our photographs can end up falling short of our expectations. So, how can we create more impressive photos? If you have an image processing app on your phone, it can automatically detect faces in a photo and you can adjust the image until you're happy with it. So, after looking around online, I found HUAWEI ML Kit's face detection capability. By integrating this capability, you can add beautification functions to your apps. Have a try! 

Application Scenarios

ML Kit's face detection capability detects up to 855 facial keypoints and returns the coordinates for the face's contour, eyebrows, eyes, nose, mouth, and ears, as well as the angle of the face. Once you've integrated this capability, you can quickly create beauty apps and enable users to add fun facial effects and features to their images. 

Posted on

How to Integrate HUAWEI ML Kit’s Hand Keypoint Detection Capability

Introduction

In the previous post, we looked at how to use HUAWEI ML Kit's skeleton detection capability to detect points such as the head, neck, shoulders, knees, and ankles. But as well as skeleton detection, ML Kit also provides a hand keypoint detection capability, which can locate 21 hand keypoints, such as fingertips, joints, and wrists. 

Application Scenarios

Hand keypoint detection is useful in a huge range of situations. For example, short video apps can generate some cute and funny special effects based on hand keypoints, to add more fun to short videos. 

Posted on

How HUAWEI ML Kit’s Face Detection and Hand Keypoint Detection Helped Create the Game Crazy Rockets

Introduction

There are so many online games these days that are addictive, easy to play, and suitable for a wide age range. I've long dreamed of creating a hit game of my own, but doing so is harder than it seems. I was researching on the Internet, and was fortunate to learn about HUAWEI ML Kit's face detection and hand keypoint detection capabilities, which make games much more engaging. 

Application Scenarios

ML Kit's face detection capability detects up to 855 keypoints of the face, and returns the coordinates for the face contours, eyebrows, eyes, nose, mouth, and ears, as well as angles. Integrating the face detection capability makes it easy to create a beauty app, or enable users to add special effects to facial images to make them more intriguing. 

Posted on

How to Implement Dictation Word Broadcast: Super Simple Integration With ML Kit Can Achieve This!

Introduction

I believe we all have dictation when we first start learning a language. Nowadays, an important after-school assignment for primary school students is the dictation of new words in the text. Many parents have this experience. On the one hand, this kind of word reading is relatively simple, and on the other hand, parents' time is precious. Nowadays, many dictations are available in the market. These speakers record the words after class in Chinese textbooks for parents to download. However, this kind of recording is not flexible enough; if the teacher left a few extra words today that were not part of the after-school exercise, the recording would not satisfy the needs of parents and children. This document describes an automatic voice broadcast app that uses the universal text recognition function and speech synthesis function of our ML kit. You only need to take photos of dictated words or texts, and then, the text in the photos can be automatically broadcast. The tone can be adjusted.

Development Preparations

1. Open the AndroidStudio project-level build.gradle file.AndroidStudio project-level build.gradle file.

Posted on

Implementing Product Visual Search

Use Case 

  • We will capture a product image from our developed shopping application using a device camera.

  • We will show the returned products list.

Prerequisites 

  • Java JDK 1.8 or higher is recommended.