terminal
Portfolio

Overview

person
🤖
Portfolio / Curriculum Vitae / Ali Mustofa

Ali Mustofa

Computer Vision & Edge AI Engineer

Available for Industrial AI & Edge Vision Projects
developer_board

Computer Vision Engineer with 5+ years of professional experience designing, developing, optimizing, and deploying production-grade Computer Vision and Edge AI systems for industrial automation.

Experience
5+ Years
Production CV Deployment
Pipeline
Sync Matrix
LiDAR + Multi-Cam + PLC
precision_manufacturing

Industrial Deployments

PT. Halotec Indonesia

2020 – Present
Computer Vision Research and Development
PythonPyTorchTensorFlowOpenCVTensorRTONNX RuntimeDockerNVIDIA JetsonFastAPIPostgreSQL
  • check_circleArchitected and deployed production-grade Computer Vision and Edge AI systems for automated industrial inspection and port operations.
  • check_circleConducted R&D and technology exploration for new Computer Vision products, evaluating emerging AI models, vision algorithms, and Edge AI technologies for potential industrial applications.
  • check_circleDeveloped AI solutions for Object Detection, Semantic Segmentation, OCR, LPR, Object Tracking, Seal Detection, and Container Damage Detection.

PT. Dinamika Metamorfosa

Jul 2019 – Sep 2019
Web Developer
PHP CodeIgniter MySQL REST APIs
  • check_circleDeveloped backend modules using PHP (CodeIgniter) and MySQL following the MVC architecture.
  • check_circleDeveloped backend modules, database integration, and application business logic
  • check_circleImplemented REST-based services and optimized database-driven application workflows.
work

Portfolio

"> arrow_right

Automated Container Inspection

Real Project

Real-time container inspection for port terminal operations. LiDAR-triggered multi-camera and line-scan pipelines read Container Number, ISO Code, and Max Gross via OCR, verify seal presence, and detect rust and damage on every side of the container — deployed on NVIDIA Jetson edge devices.

OCRDamage DetectionSeal DetectionLine-scanLiDARNVIDIA JetsonTensorRT
OCR detection of container number, ISO code and max gross weight
OCR — Container No. · ISO Code · Max Gross
Seal presence detection on container rear door
Seal Presence Detection
Side line-scan panorama with rust and tire detection
Side Line-scan — Rust & Tire Detection
Top line-scan panorama with rust detection
Top Line-scan — Rust Detection
"> arrow_right

Automated Container Crane OCR

Real Project

Gantry crane OCR portal that captures containers from 5 camera views — left, right, rear, front, and top — during crane operations. Recognizes ISO 6346 container numbers with check-digit validation, ISO size/type, and CSC plate max gross, flags seal presence status, and logs every transaction to a real-time reports dashboard with sub-second processing (200–450 ms).

OCRISO 6346Multi-Camera GantrySeal DetectionReal-time DashboardSub-second Inference
GT-OCR transaction detail view with container identification panel
Transaction Detail — Container ID · ISO · CSC Max Gross
Top camera capture of container roof during crane operation
Top View — Roof Camera
Rear camera capture with 100 percent OCR confidence
Rear View — Door End (OCR 100%)
Front camera capture of container front end
Front View (OCR 83%)
Right side capture with 97 percent OCR confidence in 200 ms
Long Side — Starboard (OCR 97% · 200 ms)
"> arrow_right

Video-to-Image Stitching

Real Project

Image processing pipeline that stitches frames from a moving top-view camera into a single full-length panorama of the container as the truck passes under the gantry — turning standard video into complete top-side inspection imagery, with frame registration and seam blending across the stitched output. One stitched image is produced per transaction for the OCR portal.

OpenCVVideo ProcessingFrame RegistrationPanorama StitchingTop-View Inspection
Stitched top view panorama of a red container from video frames
TX-2026-3877 · Red Container
Stitched top view panorama of a pink container from video frames
TX-2026-3878 · Pink Container
Stitched top view panorama of a grey container from video frames
TX-2026-3879 · Grey Container
"> arrow_right

Vector Search Product Scanner

Real Project

Live camera scanner for halal product verification, powering the Scan Aman Halal app. A captured frame of the packaging is embedded and matched against a product database through vector similarity search — instantly returning the product and its halal certificate status (name and producer). Three lookup modes: product name, packaging scan, and composition check.

Vector SearchImage EmbeddingLive CameraHalal VerificationProduct Database
Scan Aman Halal live camera scanner matching an Energen package to its halal certificate
Live Scan — Packaging Matched to Halal Certificate (Energen · PT. Tirta Fresindo Jaya)
"> arrow_right

Realtime PPE Detection

Real Project

Real-time PPE (Personal Protective Equipment) violation detection across multiple cameras in industrial container yards. The system detects persons and flags violations such as NON_HELMET and NON_VEST with severity levels, then logs every event with camera location, timestamp, and a cropped evidence snapshot into a review dashboard — where operators can add review notes and mark records reviewed, dismissed, or deleted.

Real-time DetectionPPE DetectionMulti-CameraViolation Review DashboardSafety Compliance
PPE violation detail for NON_HELMET at location 14 Selatan
Violation Detail — NON_HELMET · Loc. 14 Selatan
PPE violation detail for NON_VEST with review workflow
Violation Detail — NON_VEST · Review Workflow
"> arrow_right

Custom Vehicle Classification

Real Project

Custom vehicle classification for Indonesian toll roads (v1.0 Jasamarga) — classifies passing vehicles into the official toll classes (Golongan 1A, 1B, 2A, 2, 3) from CCTV footage in real time, deployed on NVIDIA Jetson series edge devices.

Vehicle ClassificationReal-timeCCTV FootageNVIDIA JetsonToll Road
Vehicle classification results grid v1.0 Jasamarga with Golongan labels
Results v1.0 Jasamarga — Golongan 1A · 1B · 2 · 3
"> arrow_right

Realtime Face Attendance System

Real Project

Real-time face recognition attendance system running on live CCTV — recognizes registered personnel walking through building entrances and records their attendance automatically, with identity and confidence overlay drawn on the video feed at the gate.

Face RecognitionReal-timeCCTVAttendance System
Face recognition overlay with identity and confidence on live CCTV at building entrance
Live CCTV — Identity + Confidence Overlay at the Gate
auto_stories

Latest Articles

3 Published
Build Face Search using PostgreSQL Vector
PostgreSQL Vector Search Computer Vision

Build Face Search using PostgreSQL Vector

Face recognition technology has become a key component of many applications, from security systems and mobile device authentication to personalized experiences...

Read on Medium arrow_forward
How to Fine-tuning Llama Vision OCR
LLaMA Vision OCR Fine-Tuning

How to Fine-tuning Llama Vision OCR

LLaMA OCR stands for 'Large Language Model Application Optical Character Recognition'. It's an optical character recognition pipeline leveraging multimodal LLMs...

Read on Medium arrow_forward
Training Custom Dataset YOLOv8 OBB — Oriented Bounding Boxes
YOLOv8 OBB Object Detection

Training Custom Dataset YOLOv8 OBB — Oriented Bounding Boxes

What is Oriented Bounding Boxes Object Detection? Oriented bounding boxes allow detecting objects at varying rotation angles for industrial vision...

Read on Medium arrow_forward
schema

Technical Stack

visibility Computer Vision
OpenCVYOLOSSDCRAFT OCRObject DetectionSemantic SegmentationInstance SegmentationObject TrackingImage ClassificationOCR
model_training Deep Learning & AI
PyTorchTensorFlowKerasCNNVision Transformer (ViT)Transfer LearningModel Fine-TuningData AugmentationModel EvaluationCustom Dataset
memory Edge AI & Embedded Computing
NVIDIA Jetson NanoJetson XavierJetson OrinNVIDIA DeepStreamCUDAGPU ComputingEdge AI DeploymentReal-Time Video Analytics
account_tree System Architecture
Edge AI SystemsAI Pipeline ArchitectureMicroservices ArchitectureDistributed AI SystemsEvent-Driven ArchitectureIndustrial AutomationProduction AI Systems
precision_manufacturing Industrial Integration
Siemens PLCArduinoRaspberry PiIndustrial IoTLiDAR 1D/2DSensor IntegrationHardware TriggeringEvent SynchronizationMachine-to-Machine Communication
cloud_sync AI Deployment & MLOps
DockerGitGitLab CI/CDModel DeploymentModel MonitoringContainerized AI ServicesRemote Edge DeploymentMicrosoft AzureGoogle Cloud Platform
dns Backend & API
PythonFastAPIFlaskREST APIWebSocketAPI IntegrationAsynchronous ProcessingBackend Service Development
analytics Data Processing & Analytics
NumPyPandasMatplotlibDataset ProcessingData CleaningData ValidationPerformance Analysis
school

Education & Credentials

Universitas Dian Nuswantoro B.Eng

Bachelor of Informatics Engineering • GPA: 3.3 / 4.00

Undergraduate Thesis: Panorama Reconstruction Using Farneback Optical Flow and Kalman Filter for Moving Object Mapping

SMKN 1 Jenangan Ponorogo 2019

Software Engineering (Vocational High School)

Certifications & Credentials
verified
DeepStream for Video Analytics MLOps & Deployment · NVIDIA Deep Learning Institute
Issued
verified
MLOps Essentials: Model Deployment and Monitoring MLOps & Deployment
Issued
verified
Computer Vision in Microsoft Azure & GCP Business Cloud & Platform Engineering
Issued
verified
TensorFlow for Artificial Intelligence & Deep Learning Machine Learning & Deep Learning · Coursera
Issued
verified
Machine Learning Terapan Machine Learning & Deep Learning · Dicoding
Issued
translate
TOEFL Preparation Assessment English Proficiency
Score: 550
send

Industrial Consultation

Need an on-premise vision POC, Jetson deployment optimization, or industrial OCR pipeline? Send a project brief.

Last modified by Ali MustofaVersion 4.2.1 • Prod