Using Core ML for semantic image segmentation

At a glance

Project structure

Source bundle/
├── SegmentationApp/
│   ├── SegmentationApp.swift
│   ├── ViewModel.swift
│   ├── MainView.swift
│   └── SegmentationApp.entitlements
├── Common/
│   ├── CoreImageExtensions.swift
│   └── SegmentationModelHelper.swift
├── Configuration/
│   └── SampleCode.xcconfig
└── ImageSegmentationDETR.xcodeproj/
    ├── .xcodesamplecode.plist
    └── project.pbxproj

Structure observations

• Architecturally prominent files are ranked from entry points and role-named declarations; resource-only paths are omitted.
• Primary languages: Swift.
• The verified tree contains 4 project/configuration file(s) and 6 source declaration(s).

Overall architecture

flowchart LR
    N1["SegmentationApp"]
    N2["MainView"]
    N3["ViewModel"]
    N4["CoreML APIs"]
    N1 --> N2
    N2 --> N3
    N3 --> N4

Reference code

SegmentationApp/SegmentationApp.swift:10 — architecture anchor

@main
struct CameraApp: App {
    // ...
}

Interpretation

The arrows summarize the source-visible entry, role-named types or folders, and framework direction; when nodes come from structural folders, the sequence is a high-level interpretation rather than proof that every adjacent node calls the next. Ownership is claimed only where the next section cites a stored property or assignment. The diagram is intentionally limited to the dominant path into Core ML.

Ownership and state

classDiagram
    ViewModel o-- Image : image
    ViewModel o-- Image : maskedImage
    ViewModel *-- Array : predictedLabels
    ViewModel *-- String : errorMessage

Ownership evidence

SegmentationApp/ViewModel.swift:19 — stored dependency or nearest verified ownership anchor

    @Published private(set) var image: Image?

    /// The overlay image that masks a selected label.
    @Published private(set) var maskedImage: Image?

    /// A list of predicted labels in the original image.
    @Published private(set) var predictedLabels: [String] = []

Composition arrows indicate a source-visible construction expression or locally owned value state; aggregation means the owner stores or receives a dependency without proving exclusive lifetime ownership.

Class and protocol design

SegmentationApp/SegmentationApp.swift:11 — representative type boundary

struct CameraApp: App {
    // ...
}

No local protocol conformance is claimed as protocol-oriented design; external framework conformances are listed only as dependencies.

Access control

Reference code

SegmentationApp/MainView.swift:159 — representative boundary

struct PredictedLabelGridCell: View {
    // ...
    private static let diameter = CGFloat(22)
    // ...
}

Swift declarations without a modifier are internal; explicit private, fileprivate, private(set), public, or open entries above are interpreted by language semantics. Objective-C/C samples instead rely on header and implementation boundaries, which are not equivalent to Swift lexical privacy.

Logic ownership and placement

Design patterns

Naming conventions

• Types: App: CameraApp; View: MainView, PredictedLabelsGridView; ViewModel: ViewModel.
• Protocols: no local protocol declaration in the scanned source.
• Methods: applyCustomAppearance, loadModel, selectLabel, didLoadModel, handleSelectedPhotoTransferable, handleSelectedImage, performInferenceAndUpdateUI, handlePredictionResult.
• Files: SegmentationApp/ViewModel.swift, SegmentationApp/MainView.swift.

Architecture takeaways

• SegmentationApp is the main source-visible entry or composition anchor for this sample.
• Framework work reaches SwiftUI, CoreML, CoreImage, ImageIO through a deliberately small high-level chain; the detailed API graph remains inside the cited implementation files.
• Stored-property evidence identifies lifecycle collaboration; it does not by itself prove exclusive object ownership.
• Access-control conclusions separate verified language visibility from the likely design rationale.
• The source does not justify labeling the design protocol-oriented.

Source map

• Official Apple documentation