Our Mobile Development Projects Portfolio
Abto Software with a profound experience in creating mobile applications provides mobile solutions for every smart device for all the prevalent operating systems. Our expertise in mobile development comes from years of experience. Our paramount focus is create quality-rich innovative solutions. The mobile development projects we built range from small apps to enterprise-sized products.
Take a look at some of our featured mobile apps and development projects accomplished for our global customers:
-
License Plate Recognition
Our automatic license plate recognition software is designed to detect, scan and recognise vehicle license number plates in real-time by processing video footage from CCTV camera.
Available on Android devices as a subscription service, LPR can be used to:
- Help police, or security agency scan and identify cars
- Secure border crossing by assessing if a car is suspicious
- Parking garages can automatically open just by recognizing the tenant’s plates
- Parking Service companies can better monitor entry and exit
Customer:
Tech company, Israel
Project challenges:
- Camera software works in real-time environment under any conditions: illumination, weather, etc
- Detect vehicle direction
- High software performance, since in most cases the vehicle is a moving object
- Powerful synergy with the client’s suite of vehicle recognition products
- Poor input file resolution, usually because the plate is too far away, or blurry images, particularly motion blur
- Simultaneous processing of multiple video streams from CCTV cameras on different devices
Technologies and Instruments:
- The back-end development tech stack: PHP, Laravel, Node.js, Amazon Web Services: S3, RDS, SQS, SNS, Database: MySQL
- Web UI tech stack: AngularJS, HTML, CSS
- Data Modeling and Architecture: machine learning and image/video processing algorithms, Haar Cascades
-
Intelligent Handwritten Text Recognition
For a pharmaceutical company from Belgium, we needed to develop an intelligent character recognition software that would verify tests by checking whether handwritten ID (the set of letters and numbers) on the test container matches the ID from the dataset. Every container has a label with ID and QR-Code which is used as a link to the dataset. Features include:
- Our ICR platform is a self-learning system which means the level of recognition accuracy is increased each time the application is used
- Given variances in handwriting styles, capture rates can vary dramatically, the OCR software maintains the accuracy rate of 98% if source documents are in good condition. For lower quality input files we were able to achieve an accuracy rate of 80%
Challenges:
Here is a list of problems that occurred during the development of a handwritten characters recognition application:
- poor quality text
- a variety of individual handwritings
- characters separation from the background
- a unique form of symbols
- nonlinear character location
- neighboring symbols can be connected
Intelligent Character Recognition Software
We have done a lot of work to overcome the limitations of OCR by applying preprocessing algorithms (image binarization, waste clearing, text lines detection, character detection). Overall, the handwritten character recognition can be divided into following steps:
- create a relevant training database
- run preprocessing algorithms
- correctly segment areas with numbers (our region of interest)
Technologies:
- MATLAB, Python, OpenCV, C++, Hough transformation algorithms, Android, IOS, image processing, machine learning, k-nearest neighbors algorithm (k-NN).
-
Mobile Subscription App
JustAnswer is the world’s leading expert marketplace offering fast and affordable online advice from 10,000 verified professionals. The customers with membership can use this application to communicate with the expert, as well as:
- Search for categories, upload photos
- Access to questions & answers in offline mode
- AReceive instant notification when expert replies
- Deep iPhone integration (Push Notifications, Spotlight, Keychain)
- Using third-party frameworks and services
Challenges in IOS app development:
- Convert codebase from Objective-C to Swift 3.0 in order to improve performance
- Reintegrate third-party frameworks
- Organize multiple 2-day hackathons (IP-telephony in the app, offline-mode) with further productization
Benefits:
- increased average revenue per user (ARPU) by billing customers on a recurring basis
- retained more customers by providing enough value that users continue to renew subscriptions.
Technologies:
- Objective-C, Swift 3.0, Alamofire, Google Analytics, Tag Manager, HockeyApp, Twilio, UI & load tests, CI build server.
Customer:
Tech company, Israel
Project challenges:
- Camera software works in real-time environment under any conditions: illumination, weather, etc
- Detect vehicle direction
- High software performance, since in most cases the vehicle is a moving object
- Powerful synergy with the client’s suite of vehicle recognition products
- Poor input file resolution, usually because the plate is too far away, or blurry images, particularly motion blur
- Simultaneous processing of multiple video streams from CCTV cameras on different devices
Technologies and Instruments:
- The back-end development tech stack: PHP, Laravel, Node.js, Amazon Web Services: S3, RDS, SQS, SNS, Database: MySQL.
- Web UI tech stack: AngularJS, HTML, CSS.
- Data Modeling and Architecture: machine learning and image/video processing algorithms, Haar Cascades.
Challenges:
Here is a list of problems that occurred during the development of a handwritten characters recognition application:
- poor quality text
- a variety of individual handwritings
- characters separation from the background
- a unique form of symbols
- nonlinear character location
- neighboring symbols can be connected.
Intelligent Character Recognition Software
We have done a lot of work to overcome the limitations of OCR by applying preprocessing algorithms (image binarization, waste clearing, text lines detection, character detection). Overall, the handwritten character recognition can be divided into following steps:
- create a relevant training database
- run preprocessing algorithms
- correctly segment areas with numbers (our region of interest)
Technologies:
- MATLAB, Python, OpenCV, C++, Hough transformation algorithms, Android, IOS, image processing, machine learning, k-nearest neighbors algorithm (k-NN).
Challenges in IOS app development:
- Convert codebase from Objective-C to Swift 3.0 in order to improve performance
- Reintegrate third-party frameworks
- Organize multiple 2-day hackathons (IP-telephony in the app, offline-mode) with further productization
Benefits:
- increased average revenue per user (ARPU) by billing customers on a recurring basis
- retained more customers by providing enough value that users continue to renew subscriptions.
Technologies:
- Objective-C, Swift 3.0, Alamofire, Google Analytics, Tag Manager, HockeyApp, Twilio, UI & load tests, CI build server.