Mobile & Industrial Inspection

FinDensity - MAHLE Camera-Based Fin Density Measurement iOS App

An iOS image-processing app for MAHLE that measures cooling-fin density on components using the device camera. The user captures and crops an image of the finned surface, and pixel-based detection counts the fins over a measured distance to compute fins count, total distance and fins density - a dimensional inspection metric for heat-exchanger / radiator parts.

01 Overview

An iOS image-processing app for MAHLE that measures cooling-fin density on components using the device camera. The user captures and crops an image of the finned surface, and pixel-based detection counts the fins over a measured distance to compute fins count, total distance and fins density - a dimensional inspection metric for heat-exchanger / radiator parts.

Scope of delivery

Built the FinDensity iOS app for MAHLE. Developed a custom AVCapture camera screen with focus-square framing and image cropping, an Objective-C ImageProcessor (OpenCV-backed) that runs pixel-level analysis to detect and count fins on the captured surface, and a ScanResult screen that reports fins count, total distance and fins density, with part-number tagging and history saved via an FMDB SQLite database.

02 Business Challenge

An iOS image-processing app for MAHLE that measures cooling-fin density on components using the device camera. The user captures and crops an image of the finned surface, and pixel-based detection counts the fins over a measured distance to compute fins count, total distance and fins density - a dimensional inspection metric for heat-exchanger / radiator parts.

03 Our Solution

Built the FinDensity iOS app for MAHLE. Developed a custom AVCapture camera screen with focus-square framing and image cropping, an Objective-C ImageProcessor (OpenCV-backed) that runs pixel-level analysis to detect and count fins on the captured surface, and a ScanResult screen that reports fins count, total distance and fins density, with part-number tagging and history saved via an FMDB SQLite database.

Engineering approach

Engineered raw-RGBA pixel analysis (processUsingPixels) that walks the captured image rows to locate and count fin edges, exposes the result through an ImageProcessor delegate, and converts between camera-cropped pixel dimensions and on-screen distance to compute fins per unit length. Persisted each scan with part metadata and timestamps for the 'Previous Scans' list via FMDB.

04 Design Thinking

Scope reviewArchitecture mappingBuildLaunch

05 Technical Architecture

Architecture summary: Engineered raw-RGBA pixel analysis (processUsingPixels) that walks the captured image rows to locate and count fin edges, exposes the result through an ImageProcessor delegate, and converts between camera-cropped pixel dimensions and on-screen distance to compute fins per unit length. Persisted each scan with part metadata and timestamps for the 'Previous Scans' list via FMDB.

06 Technology Stack

SwiftObjective-COpenCV (iOS Framework)AVFoundation (Camera)FMDB / SQLiteCoreMotionPhotosUIUIKit (MVC)

07 Development Timeline

Delivered through structured phases - discovery, design, build, integration, and launch - with iterative releases and ongoing enhancements across a mobile & industrial inspection delivery.

08 UI Screens / Key Features Showcase

09 Before vs After

Before

Manual, disconnected workflows and limited visibility across operations.

After

An integrated, automated mobile & industrial inspection solution with a unified experience, stronger controls and measurable efficiency.

10 Performance Metrics

99.9%System SLA
< 90msResponse Time
High EfficiencyClient Impact

11 Business Outcomes

Outcomes available on request.

12 Testimonial & Connect

Project delivered by the Dogra Technologies engineering team.

Interested in a similar solution?

Request Architecture Brief View Full Portfolio