# heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin architecture

> Architecture diagram of the GitHub repository heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-03-30). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin
- Repository: https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin

## Overview

1. **Repository purpose and overall shape**
   This repo is a stepwise computer-vision pipeline for packaged meat inspection on a production line. It evolves from simple RTSP frame capture to motion-triggered snapshotting, barcode reading, product/area cropping, OCR for date reading, and later evaluation of real-time feasibility. The code is organized by milestone folders (`seminar2`–`seminar7`, `ettevalmistus3`–`ettevalmistus6`), each representing a distinct stage of the pipeline.

2. **Primary runtime boundary: RTSP video ingestion**
   The upstream data source is an RTSP camera stream, referenced in the README as `rtsp://172.17.37.81:8554/<toode>`. Early scripts in `seminar2`, `ettevalmistus3`, and `ettevalmistus4` handle reading frames from the stream and deciding when to save a frame based on motion or visual markers. This is the entry boundary for the whole system.

3. **Stage 1: motion and trigger detection**
   `ettevalmistus3/RTSP_liikumine.py` and related `seminar2/RTSP_*` scripts implement the first control logic: detect movement, determine when a product has stopped, and choose a usable frame. This stage reduces a continuous stream into discrete candidate images for downstream processing. It is the first major filtering point in the architecture.

4. **Stage 2: barcode reading and product metadata mapping**
   `seminar3/yl1_triipkoodi_lugemine_run.py`, `seminar3/yl2_toote_info_run.py`, and supporting files like `barcode_tools.py` and `barcode_data.json` form the barcode subsystem. The barcode reader is a concrete external dependency here: Dynamsoft barcode reading is used to decode codes from saved images. The decoded barcode is then mapped to product metadata such as product name and shelf-life information.

5. **Integrated snapshot pipeline**
   `ettevalmistus4/RTSP_liikumine_es4.py` combines movement-triggered capture with barcode extraction into a more complete “tick-based” workflow. Each trigger produces a time-stamped product observation containing barcode and product metadata. This stage bridges raw video acquisition and structured inspection output.

6. **Stage 3: geometric cropping of product regions**
   `seminar4/yl1_toodete_cut.py`, `seminar4/yl2_alade_cut.py`, `seminar4/alade_cut.py`, and `seminar4/toodete_cut_lahendus.py` implement the slicing subsystem. Here, full-frame product images are normalized: the product is isolated, rotated/oriented, resized, and then smaller regions are cut out for later tasks such as date OCR or label analysis. This is a major boundary: the pipeline changes from “whole-frame inspection” to “region-of-interest processing.”

7. **RTSP slicing as a reusable pipeline**
   `ettevalmistus5/yl1_rtsp_slicing.py` moves the cropping logic back into the live RTSP flow. It supports offline replay from saved data and debugging of crop quality. The `ettevalmistus5` folder contains the intermediate artifacts and helper code needed to make this stage reproducible, including templates and barcode metadata. This is where the system becomes a reusable end-to-end capture-and-crop service.

8. **OCR experimentation and model comparison**
   `seminar5/yl1_OCR.py`, `seminar5/yl2_OCR.py`, and especially `seminar5/ocr_compare.py` compare different OCR approaches for reading dates from the cropped regions. The repo explicitly treats OCR as a pluggable subsystem: local models and cloud-backed OpenRouter workflows are compared for accuracy, speed, and cost. This stage consumes the cropped date/label images produced earlier, not raw video.

9. **Real-time date recognition pipeline**
   `ettevalmistus6/RTSP_with_date.py` is the integration point for live date detection. It combines RTSP capture, barcode identification, crop extraction, and OCR into one real-time pipeline, with attention to throughput and alert logic. The `ettevalmistus6` data and answer files suggest this stage is also used for reporting and evaluation against a target takt time.

10. **Evaluation and experiment outputs**
   `seminar6` adds a measurement layer around detection quality. The `results/` directory stores per-product JSON metrics for DINO and MAE-based experiments, along with histogram PDFs. This makes the architecture not only a production pipeline but also an experiment harness: model outputs are logged and compared across products and label types.

11. **Latest model-based classification experiments**
   `seminar7` appears to be a later experimental branch focused on threaded RTSP processing and learned classification. Files such as `RTSP_threadded.py`, `sildid_DINO.py`, `logistic_regression.py`, and `toodete_tuvastamine.py` suggest a model pipeline using DINO embeddings plus logistic regression to classify product/label regions. The folder structure with `product_area` samples per product indicates a dataset boundary for supervised learning experiments, separate from the earlier rule-based OCR flow.

12. **Data, templates, and artifacts are first-class inputs**
   Several folders contain JSON templates, barcode metadata, sample crops, generated PDFs, and result files. These are not just outputs; they are part of the system’s architecture because each stage depends on specific intermediate artifacts from the previous stage. The key boundary is that each milestone folder is self-contained, with its own sample data and evaluation outputs, rather than one global shared dataset.

13. **Environment and external dependencies**
   The project is designed around a Conda environment (`dependencies/environment.yml`, Python 3.11). The architecture depends materially on OpenCV for image/video handling, Dynamsoft for barcode decoding, Pillow/numpy/matplotlib for image processing and analysis, and optionally EasyOCR / Torch / Strhub / PaddleX for OCR comparisons. OpenRouter is an optional external service used in OCR evaluation, controlled by `OPENROUTER_API_KEY`.

14. **What an architecture diagram should emphasize**
   The clearest system view is a left-to-right pipeline: RTSP stream → motion/trigger detection → snapshot capture → barcode decoding and product metadata lookup → product normalization/cropping → OCR or model-based inspection → metrics/reporting. The folders map naturally onto stages, and the main architectural boundaries are between live video ingestion, intermediate image artifacts, and evaluation/modeling experiments.

Main entry points: [`seminar6/RTSP_with_date.py`](https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/seminar6/RTSP_with_date.py) (Live date), [`ettevalmistus4/RTSP_liikumine_es4.py`](https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/ettevalmistus4/RTSP_liikumine_es4.py) (Tick pipeline), [`seminar3/yl1_triipkoodi_lugemine_run.py`](https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/seminar3/yl1_triipkoodi_lugemine_run.py) (Decode code), [`seminar4/yl1_toodete_cut.py`](https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/seminar4/yl1_toodete_cut.py) (Product cut)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_g1["Live capture"]
  node_rtsp_source(("RTSP stream<br/>camera feed"))
  node_seminar2_capture["Frame read<br/>capture script<br/>[RTSP_lugemine.py]"]
  node_ettevalmistus3_motion["Motion trigger<br/>trigger logic<br/>[RTSP_liikumine.py]"]
  node_ettevalmistus4_tick["Tick pipeline<br/>integrated capture"]
end

subgraph group_g2["Barcode stage"]
  node_barcode_tools["Barcode tools<br/>helper module<br/>[barcode_tools.py]"]
  node_barcode_read["Decode code<br/>barcode reader"]
  node_product_info["Map product<br/>metadata lookup"]
end

subgraph group_g3["Cropping stage"]
  node_product_cut["Product cut<br/>crop pipeline<br/>[yl1_toodete_cut.py]"]
  node_area_cut["Area cut<br/>roi extraction<br/>[yl2_alade_cut.py]"]
  node_cut_solution["Cut solution<br/>crop refinement"]
  node_rtsp_slicing["RTSP slicing<br/>live crop pipeline"]
end

subgraph group_g4["OCR stage"]
  node_ocr_compare["OCR compare<br/>benchmarking<br/>[ocr_compare.py]"]
  node_ocr_local["Local OCR<br/>ocr script<br/>[yl1_OCR.py]"]
  node_ocr_cloud["Cloud OCR<br/>ocr script<br/>[yl2_OCR.py]"]
  node_date_rtsp["Live date<br/>realtime pipeline<br/>[RTSP_with_date.py]"]
end

subgraph group_g5["Experimentation"]
  node_dino_eval["DINO eval<br/>metrics script<br/>[sildid_DINO.py]"]
  node_mae_eval["MAE eval<br/>metrics script<br/>[sildid_MAE.py]"]
  node_threaded_rtsp["Threaded RTSP<br/>parallel capture<br/>[RTSP_threadded.py]"]
  node_classifier["Classifier<br/>learned model"]
  node_dino_classify["DINO classify<br/>embedding pipeline<br/>[sildid_DINO.py]"]
  node_inspect_products["Product detect<br/>inspection pipeline"]
end

subgraph group_g6["Artifacts"]
  node_barcode_data["Barcode map<br/>reference data<br/>[barcode_data.json]"]
  node_results["Results<br/>metrics artifacts"]
end

subgraph group_g7["Environment"]
  node_environment["Env spec<br/>dependency manifest<br/>[environment.yml]"]
end

node_rtsp_source -->|"frames"| node_seminar2_capture
node_seminar2_capture -->|"trigger"| node_ettevalmistus3_motion
node_ettevalmistus3_motion -->|"snapshot"| node_ettevalmistus4_tick
node_ettevalmistus4_tick -->|"decode"| node_barcode_read
node_barcode_read -->|"helpers"| node_barcode_tools
node_barcode_read -->|"code"| node_product_info
node_product_info -->|"lookup"| node_barcode_data
node_ettevalmistus4_tick -->|"crop"| node_product_cut
node_product_cut -->|"roi"| node_area_cut
node_area_cut -.->|"refine"| node_cut_solution
node_product_cut -->|"live flow"| node_rtsp_slicing
node_rtsp_slicing -->|"crops"| node_ocr_compare
node_ocr_compare -->|"compare"| node_ocr_local
node_ocr_compare -->|"compare"| node_ocr_cloud
node_ocr_local -->|"integrate"| node_date_rtsp
node_ocr_cloud -.->|"integrate"| node_date_rtsp
node_date_rtsp -->|"measure"| node_results
node_dino_eval -->|"write"| node_results
node_mae_eval -->|"write"| node_results
node_threaded_rtsp -->|"features"| node_dino_classify
node_dino_classify -->|"predict"| node_classifier
node_inspect_products -->|"stream"| node_threaded_rtsp
node_inspect_products -->|"learned vision"| node_dino_classify
node_environment -.->|"runtime"| node_seminar2_capture
node_environment -.->|"runtime"| node_date_rtsp

click node_seminar2_capture "https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/seminar2/RTSP_lugemine.py"
click node_ettevalmistus3_motion "https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/ettevalmistus3/RTSP_liikumine.py"
click node_ettevalmistus4_tick "https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/ettevalmistus4/RTSP_liikumine_es4.py"
click node_barcode_tools "https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/seminar3/barcode_tools.py"
click node_barcode_read "https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/seminar3/yl1_triipkoodi_lugemine_run.py"
click node_product_info "https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/seminar3/yl2_toote_info_run.py"
click node_barcode_data "https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/seminar3/barcode_data.json"
click node_product_cut "https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/seminar4/yl1_toodete_cut.py"
click node_area_cut "https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/seminar4/yl2_alade_cut.py"
click node_cut_solution "https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/seminar4/toodete_cut_lahendus.py"
click node_rtsp_slicing "https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/ettevalmistus5/yl1_rtsp_slicing.py"
click node_ocr_compare "https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/seminar5/ocr_compare.py"
click node_ocr_local "https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/seminar5/yl1_OCR.py"
click node_ocr_cloud "https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/seminar5/yl2_OCR.py"
click node_date_rtsp "https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/seminar6/RTSP_with_date.py"
click node_dino_eval "https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/seminar6/sildid_DINO.py"
click node_mae_eval "https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/seminar6/sildid_MAE.py"
click node_threaded_rtsp "https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/seminar7/RTSP_threadded.py"
click node_classifier "https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/seminar7/logistic_regression.py"
click node_dino_classify "https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/seminar7/sildid_DINO.py"
click node_inspect_products "https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/seminar7/toodete_tuvastamine.py"
click node_results "https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/tree/main/seminar6/results"
click node_environment "https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/dependencies/environment.yml"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_rtsp_source,node_seminar2_capture,node_ettevalmistus3_motion,node_ettevalmistus4_tick,node_environment toneBlue
class node_barcode_tools,node_barcode_read,node_product_info toneAmber
class node_product_cut,node_area_cut,node_cut_solution,node_rtsp_slicing toneMint
class node_ocr_compare,node_ocr_local,node_ocr_cloud,node_date_rtsp toneRose
class node_dino_eval,node_mae_eval,node_threaded_rtsp,node_classifier,node_dino_classify,node_inspect_products toneIndigo
class node_barcode_data,node_results toneTeal
```

## Components

### Live capture

RTSP ingestion and trigger detection stages.

- **RTSP stream**: camera feed · Production-line video source referenced by the pipeline.
- [Frame read](https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/seminar2/RTSP_lugemine.py): capture script · Early RTSP frame capture and visual trigger experimentation. · `seminar2/RTSP_lugemine.py`
- [Motion trigger](https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/ettevalmistus3/RTSP_liikumine.py): trigger logic · Detects movement and selects a usable frame once product motion settles. · `ettevalmistus3/RTSP_liikumine.py`
- [Tick pipeline](https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/ettevalmistus4/RTSP_liikumine_es4.py): integrated capture · Combines movement-triggered capture with barcode extraction. · `ettevalmistus4/RTSP_liikumine_es4.py`

### Barcode stage

Decode barcodes and map them to product metadata.

- [Barcode tools](https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/seminar3/barcode_tools.py): helper module · Shared barcode parsing and lookup helpers. · `seminar3/barcode_tools.py`
- [Decode code](https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/seminar3/yl1_triipkoodi_lugemine_run.py): barcode reader · Runs barcode recognition on captured images. · `seminar3/yl1_triipkoodi_lugemine_run.py`
- [Map product](https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/seminar3/yl2_toote_info_run.py): metadata lookup · Maps decoded barcodes to product name and shelf-life data. · `seminar3/yl2_toote_info_run.py`

### Cropping stage

Normalize products and extract regions of interest.

- [Product cut](https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/seminar4/yl1_toodete_cut.py): crop pipeline · Normalizes product images before downstream inspection. · `seminar4/yl1_toodete_cut.py`
- [Area cut](https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/seminar4/yl2_alade_cut.py): roi extraction · Extracts smaller inspection regions from the product image. · `seminar4/yl2_alade_cut.py`
- [Cut solution](https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/seminar4/toodete_cut_lahendus.py): crop refinement · Alternative or improved product/area cutting implementation. · `seminar4/toodete_cut_lahendus.py`
- [RTSP slicing](https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/ettevalmistus5/yl1_rtsp_slicing.py): live crop pipeline · Brings cropping logic into the live RTSP flow. · `ettevalmistus5/yl1_rtsp_slicing.py`

### OCR stage

Date reading and OCR comparison pipelines.

- [OCR compare](https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/seminar5/ocr_compare.py): benchmarking · Compares OCR approaches for reading dates from cropped regions. · `seminar5/ocr_compare.py`
- [Local OCR](https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/seminar5/yl1_OCR.py): ocr script · Runs the local OCR approach on cropped date images. · `seminar5/yl1_OCR.py`
- [Cloud OCR](https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/seminar5/yl2_OCR.py): ocr script · Runs the alternative OCR workflow for comparison. · `seminar5/yl2_OCR.py`
- [Live date](https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/seminar6/RTSP_with_date.py): realtime pipeline · End-to-end live date recognition over RTSP. · `seminar6/RTSP_with_date.py`

### Experimentation

Evaluation, metrics, and learned classification experiments.

- [DINO eval](https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/seminar6/sildid_DINO.py): metrics script · Evaluates DINO-style product/label experiments and writes metrics. · `seminar6/sildid_DINO.py`
- [MAE eval](https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/seminar6/sildid_MAE.py): metrics script · Evaluates MAE-style experiments for the same inspection targets. · `seminar6/sildid_MAE.py`
- [Threaded RTSP](https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/seminar7/RTSP_threadded.py): parallel capture · Threaded RTSP processing for later-stage experimentation. · `seminar7/RTSP_threadded.py`
- [Classifier](https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/seminar7/logistic_regression.py): learned model · Logistic-regression classifier over learned features. · `seminar7/logistic_regression.py`
- [DINO classify](https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/seminar7/sildid_DINO.py): embedding pipeline · Uses DINO embeddings for product/label classification experiments. · `seminar7/sildid_DINO.py`
- [Product detect](https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/seminar7/toodete_tuvastamine.py): inspection pipeline · Combines detection and classification for product-area samples. · `seminar7/toodete_tuvastamine.py`

### Artifacts

Shared templates, barcode maps, and result outputs.

- [Barcode map](https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/seminar3/barcode_data.json): reference data · Product barcode metadata used across inspection stages. · `seminar3/barcode_data.json`
- [Results](https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/tree/main/seminar6/results): metrics artifacts · Stored metrics, histograms, and experiment outputs. · `seminar6/results`

### Environment

Runtime and dependency specification.

- [Env spec](https://github.com/heiliaavola/tehisintellekti_rakendmise_projekt_tooteliin/blob/main/dependencies/environment.yml): dependency manifest · Conda environment and package requirements for the pipeline. · `dependencies/environment.yml`

## Connections

- RTSP stream → Frame read: frames · Initial live video ingestion.
- Frame read → Motion trigger: trigger · Motion logic filters continuous frames into candidates.
- Motion trigger → Tick pipeline: snapshot · Captured frames feed the integrated tick-based pipeline.
- Tick pipeline → Decode code: decode · Snapshots are sent to barcode reading.
- Decode code → Barcode tools: helpers · Uses shared barcode utilities.
- Decode code → Map product: code · Decoded barcode is mapped to product metadata.
- Map product → Barcode map: lookup · Reads the shared barcode reference table.
- Tick pipeline → Product cut: crop · Inspection frames are normalized into product regions.
- Product cut → Area cut: roi · Product regions are further sliced into areas of interest.
- Area cut → Cut solution: refine · Alternative crop logic improves region extraction.
- Product cut → RTSP slicing: live flow · Crop logic is reused in the RTSP-based slicing pipeline.
- RTSP slicing → OCR compare: crops · Cropped date regions are benchmarked by OCR approaches.
- OCR compare → Local OCR: compare · One branch uses the local OCR implementation.
- OCR compare → Cloud OCR: compare · One branch uses the cloud-backed OCR implementation.
- Local OCR → Live date: integrate · Local OCR feeds the real-time date pipeline.
- Cloud OCR → Live date: integrate · Cloud OCR can also feed the real-time date pipeline.
- Live date → Results: measure · Real-time pipeline outputs are evaluated and stored.
- DINO eval → Results: write · DINO experiments generate metrics artifacts.
- MAE eval → Results: write · MAE experiments generate metrics artifacts.
- Threaded RTSP → DINO classify: features · Threaded live capture supports embedding-based classification.
- DINO classify → Classifier: predict · Learned classifier consumes embeddings.
- Product detect → Threaded RTSP: stream · Later product detection experiments reuse threaded capture.
- Product detect → DINO classify: learned vision · Classification experiments operate on product-area samples.
- Env spec → Frame read: runtime · Common Python environment supports the pipeline stages.
- Env spec → Live date: runtime · Common Python environment supports the live OCR pipeline.
